20220722.md

ArXiv cs.CV --Fri, 22 Jul 2022

1.Online Domain Adaptation for Semantic Segmentation in Ever-Changing Conditions ⬇️

Unsupervised Domain Adaptation (UDA) aims at reducing the domain gap between training and testing data and is, in most cases, carried out in offline manner. However, domain changes may occur continuously and unpredictably during deployment (e.g. sudden weather changes). In such conditions, deep neural networks witness dramatic drops in accuracy and offline adaptation may not be enough to contrast it. In this paper, we tackle Online Domain Adaptation (OnDA) for semantic segmentation. We design a pipeline that is robust to continuous domain shifts, either gradual or sudden, and we evaluate it in the case of rainy and foggy scenarios. Our experiments show that our framework can effectively adapt to new domains during deployment, while not being affected by catastrophic forgetting of the previous domains.

2.TinyViT: Fast Pretraining Distillation for Small Vision Transformers ⬇️

Vision transformer (ViT) recently has drawn great attention in computer vision due to its remarkable model capability. However, most prevailing ViT models suffer from huge number of parameters, restricting their applicability on devices with limited resources. To alleviate this issue, we propose TinyViT, a new family of tiny and efficient small vision transformers pretrained on large-scale datasets with our proposed fast distillation framework. The central idea is to transfer knowledge from large pretrained models to small ones, while enabling small models to get the dividends of massive pretraining data. More specifically, we apply distillation during pretraining for knowledge transfer. The logits of large teacher models are sparsified and stored in disk in advance to save the memory cost and computation overheads. The tiny student transformers are automatically scaled down from a large pretrained model with computation and parameter constraints. Comprehensive experiments demonstrate the efficacy of TinyViT. It achieves a top-1 accuracy of 84.8% on ImageNet-1k with only 21M parameters, being comparable to Swin-B pretrained on ImageNet-21k while using 4.2 times fewer parameters. Moreover, increasing image resolutions, TinyViT can reach 86.5% accuracy, being slightly better than Swin-L while using only 11% parameters. Last but not the least, we demonstrate a good transfer ability of TinyViT on various downstream tasks. Code and models are available at this https URL.

3.Exploring Fine-Grained Audiovisual Categorization with the SSW60 Dataset ⬇️

We present a new benchmark dataset, Sapsucker Woods 60 (SSW60), for advancing research on audiovisual fine-grained categorization. While our community has made great strides in fine-grained visual categorization on images, the counterparts in audio and video fine-grained categorization are relatively unexplored. To encourage advancements in this space, we have carefully constructed the SSW60 dataset to enable researchers to experiment with classifying the same set of categories in three different modalities: images, audio, and video. The dataset covers 60 species of birds and is comprised of images from existing datasets, and brand new, expert-curated audio and video datasets. We thoroughly benchmark audiovisual classification performance and modality fusion experiments through the use of state-of-the-art transformer methods. Our findings show that performance of audiovisual fusion methods is better than using exclusively image or audio based methods for the task of video classification. We also present interesting modality transfer experiments, enabled by the unique construction of SSW60 to encompass three different modalities. We hope the SSW60 dataset and accompanying baselines spur research in this fascinating area.

4.Neural Pixel Composition: 3D-4D View Synthesis from Multi-Views ⬇️

We present Neural Pixel Composition (NPC), a novel approach for continuous 3D-4D view synthesis given only a discrete set of multi-view observations as input. Existing state-of-the-art approaches require dense multi-view supervision and an extensive computational budget. The proposed formulation reliably operates on sparse and wide-baseline multi-view imagery and can be trained efficiently within a few seconds to 10 minutes for hi-res (12MP) content, i.e., 200-400X faster convergence than existing methods. Crucial to our approach are two core novelties: 1) a representation of a pixel that contains color and depth information accumulated from multi-views for a particular location and time along a line of sight, and 2) a multi-layer perceptron (MLP) that enables the composition of this rich information provided for a pixel location to obtain the final color output. We experiment with a large variety of multi-view sequences, compare to existing approaches, and achieve better results in diverse and challenging settings. Finally, our approach enables dense 3D reconstruction from sparse multi-views, where COLMAP, a state-of-the-art 3D reconstruction approach, struggles.

5.Generalizable Patch-Based Neural Rendering ⬇️

Neural rendering has received tremendous attention since the advent of Neural Radiance Fields (NeRF), and has pushed the state-of-the-art on novel-view synthesis considerably. The recent focus has been on models that overfit to a single scene, and the few attempts to learn models that can synthesize novel views of unseen scenes mostly consist of combining deep convolutional features with a NeRF-like model. We propose a different paradigm, where no deep features and no NeRF-like volume rendering are needed. Our method is capable of predicting the color of a target ray in a novel scene directly, just from a collection of patches sampled from the scene. We first leverage epipolar geometry to extract patches along the epipolar lines of each reference view. Each patch is linearly projected into a 1D feature vector and a sequence of transformers process the collection. For positional encoding, we parameterize rays as in a light field representation, with the crucial difference that the coordinates are canonicalized with respect to the target ray, which makes our method independent of the reference frame and improves generalization. We show that our approach outperforms the state-of-the-art on novel view synthesis of unseen scenes even when being trained with considerably less data than prior work.

6.In Defense of Online Models for Video Instance Segmentation ⬇️

In recent years, video instance segmentation (VIS) has been largely advanced by offline models, while online models gradually attracted less attention possibly due to their inferior performance. However, online methods have their inherent advantage in handling long video sequences and ongoing videos while offline models fail due to the limit of computational resources. Therefore, it would be highly desirable if online models can achieve comparable or even better performance than offline models. By dissecting current online models and offline models, we demonstrate that the main cause of the performance gap is the error-prone association between frames caused by the similar appearance among different instances in the feature space. Observing this, we propose an online framework based on contrastive learning that is able to learn more discriminative instance embeddings for association and fully exploit history information for stability. Despite its simplicity, our method outperforms all online and offline methods on three benchmarks. Specifically, we achieve 49.5 AP on YouTube-VIS 2019, a significant improvement of 13.2 AP and 2.1 AP over the prior online and offline art, respectively. Moreover, we achieve 30.2 AP on OVIS, a more challenging dataset with significant crowding and occlusions, surpassing the prior art by 14.8 AP. The proposed method won first place in the video instance segmentation track of the 4th Large-scale Video Object Segmentation Challenge (CVPR2022). We hope the simplicity and effectiveness of our method, as well as our insight into current methods, could shed light on the exploration of VIS models.

7.Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wild ⬇️

Recognizing scenes and objects in 3D from a single image is a longstanding goal of computer vision with applications in robotics and AR/VR. For 2D recognition, large datasets and scalable solutions have led to unprecedented advances. In 3D, existing benchmarks are small in size and approaches specialize in few object categories and specific domains, e.g. urban driving scenes. Motivated by the success of 2D recognition, we revisit the task of 3D object detection by introducing a large benchmark, called Omni3D. Omni3D re-purposes and combines existing datasets resulting in 234k images annotated with more than 3 million instances and 97 categories.3D detection at such scale is challenging due to variations in camera intrinsics and the rich diversity of scene and object types. We propose a model, called Cube R-CNN, designed to generalize across camera and scene types with a unified approach. We show that Cube R-CNN outperforms prior works on the larger Omni3D and existing benchmarks. Finally, we prove that Omni3D is a powerful dataset for 3D object recognition, show that it improves single-dataset performance and can accelerate learning on new smaller datasets via pre-training.

8.Novel Class Discovery without Forgetting ⬇️

Humans possess an innate ability to identify and differentiate instances that they are not familiar with, by leveraging and adapting the knowledge that they have acquired so far. Importantly, they achieve this without deteriorating the performance on their earlier learning. Inspired by this, we identify and formulate a new, pragmatic problem setting of NCDwF: Novel Class Discovery without Forgetting, which tasks a machine learning model to incrementally discover novel categories of instances from unlabeled data, while maintaining its performance on the previously seen categories. We propose 1) a method to generate pseudo-latent representations which act as a proxy for (no longer available) labeled data, thereby alleviating forgetting, 2) a mutual-information based regularizer which enhances unsupervised discovery of novel classes, and 3) a simple Known Class Identifier which aids generalized inference when the testing data contains instances form both seen and unseen categories. We introduce experimental protocols based on CIFAR-10, CIFAR-100 and ImageNet-1000 to measure the trade-off between knowledge retention and novel class discovery. Our extensive evaluations reveal that existing models catastrophically forget previously seen categories while identifying novel categories, while our method is able to effectively balance between the competing objectives. We hope our work will attract further research into this newly identified pragmatic problem setting.

9.Generative Multiplane Images: Making a 2D GAN 3D-Aware ⬇️

What is really needed to make an existing 2D GAN 3D-aware? To answer this question, we modify a classical GAN, i.e., StyleGANv2, as little as possible. We find that only two modifications are absolutely necessary: 1) a multiplane image style generator branch which produces a set of alpha maps conditioned on their depth; 2) a pose-conditioned discriminator. We refer to the generated output as a 'generative multiplane image' (GMPI) and emphasize that its renderings are not only high-quality but also guaranteed to be view-consistent, which makes GMPIs different from many prior works. Importantly, the number of alpha maps can be dynamically adjusted and can differ between training and inference, alleviating memory concerns and enabling fast training of GMPIs in less than half a day at a resolution of $1024^2$. Our findings are consistent across three challenging and common high-resolution datasets, including FFHQ, AFHQv2, and MetFaces.

10.A Dynamical Systems Algorithm for Clustering in Hyperspectral Imagery ⬇️

In this paper we present a new dynamical systems algorithm for clustering in hyperspectral images. The main idea of the algorithm is that data points are pushed' in the direction of increasing density and groups of pixels that end up in the same dense regions belong to the same class. This is essentially a numerical solution of the differential equation defined by the gradient of the density of data points on the data manifold. The number of classes is automated and the resulting clustering can be extremely accurate. In addition to providing a accurate clustering, this algorithm presents a new tool for understanding hyperspectral data in high dimensions. We evaluate the algorithm on the Urban (Available at this http URL) scene comparing performance against the k-means algorithm using pre-identified classes of materials as ground truth.

11.MetaComp: Learning to Adapt for Online Depth Completion ⬇️

Relying on deep supervised or self-supervised learning, previous methods for depth completion from paired single image and sparse depth data have achieved impressive performance in recent years. However, facing a new environment where the test data occurs online and differs from the training data in the RGB image content and depth sparsity, the trained model might suffer severe performance drop. To encourage the trained model to work well in such conditions, we expect it to be capable of adapting to the new environment continuously and effectively. To achieve this, we propose MetaComp. It utilizes the meta-learning technique to simulate adaptation policies during the training phase, and then adapts the model to new environments in a self-supervised manner in testing. Considering that the input is multi-modal data, it would be challenging to adapt a model to variations in two modalities simultaneously, due to significant differences in structure and form of the two modal data. Therefore, we further propose to disentangle the adaptation procedure in the basic meta-learning training into two steps, the first one focusing on the depth sparsity while the second attending to the image content. During testing, we take the same strategy to adapt the model online to new multi-modal data. Experimental results and comprehensive ablations show that our MetaComp is capable of adapting to the depth completion in a new environment effectively and robust to changes in different modalities.

12.A Dense Material Segmentation Dataset for Indoor and Outdoor Scene Parsing ⬇️

A key algorithm for understanding the world is material segmentation, which assigns a label (metal, glass, etc.) to each pixel. We find that a model trained on existing data underperforms in some settings and propose to address this with a large-scale dataset of 3.2 million dense segments on 44,560 indoor and outdoor images, which is 23x more segments than existing data. Our data covers a more diverse set of scenes, objects, viewpoints and materials, and contains a more fair distribution of skin types. We show that a model trained on our data outperforms a state-of-the-art model across datasets and viewpoints. We propose a large-scale scene parsing benchmark and baseline of 0.729 per-pixel accuracy, 0.585 mean class accuracy and 0.420 mean IoU across 46 materials.

13.Deep Statistic Shape Model for Myocardium Segmentation ⬇️

Accurate segmentation and motion estimation of myocardium have always been important in clinic field, which essentially contribute to the downstream diagnosis. However, existing methods cannot always guarantee the shape integrity for myocardium segmentation. In addition, motion estimation requires point correspondence on the myocardium region across different frames. In this paper, we propose a novel end-to-end deep statistic shape model to focus on myocardium segmentation with both shape integrity and boundary correspondence preserving. Specifically, myocardium shapes are represented by a fixed number of points, whose variations are extracted by Principal Component Analysis (PCA). Deep neural network is used to predict the transformation parameters (both affine and deformation), which are then used to warp the mean point cloud to the image domain. Furthermore, a differentiable rendering layer is introduced to incorporate mask supervision into the framework to learn more accurate point clouds. In this way, the proposed method is able to consistently produce anatomically reasonable segmentation mask without post processing. Additionally, the predicted point cloud guarantees boundary correspondence for sequential images, which contributes to the downstream tasks, such as the motion estimation of myocardium. We conduct several experiments to demonstrate the effectiveness of the proposed method on several benchmark datasets.

14.Approximate Differentiable Rendering with Algebraic Surfaces ⬇️

Differentiable renderers provide a direct mathematical link between an object's 3D representation and images of that object. In this work, we develop an approximate differentiable renderer for a compact, interpretable representation, which we call Fuzzy Metaballs. Our approximate renderer focuses on rendering shapes via depth maps and silhouettes. It sacrifices fidelity for utility, producing fast runtimes and high-quality gradient information that can be used to solve vision tasks. Compared to mesh-based differentiable renderers, our method has forward passes that are 5x faster and backwards passes that are 30x faster. The depth maps and silhouette images generated by our method are smooth and defined everywhere. In our evaluation of differentiable renderers for pose estimation, we show that our method is the only one comparable to classic techniques. In shape from silhouette, our method performs well using only gradient descent and a per-pixel loss, without any surrogate losses or regularization. These reconstructions work well even on natural video sequences with segmentation artifacts. Project page: this https URL

15.Boosting 3D Object Detection via Object-Focused Image Fusion ⬇️

3D object detection has achieved remarkable progress by taking point clouds as the only input. However, point clouds often suffer from incomplete geometric structures and the lack of semantic information, which makes detectors hard to accurately classify detected objects. In this work, we focus on how to effectively utilize object-level information from images to boost the performance of point-based 3D detector. We present DeMF, a simple yet effective method to fuse image information into point features. Given a set of point features and image feature maps, DeMF adaptively aggregates image features by taking the projected 2D location of the 3D point as reference. We evaluate our method on the challenging SUN RGB-D dataset, improving state-of-the-art results by a large margin (+2.1 mAP@0.25 and +2.3mAP@0.5). Code is available at this https URL.

16.Designing An Illumination-Aware Network for Deep Image Relighting ⬇️

Lighting is a determining factor in photography that affects the style, expression of emotion, and even quality of images. Creating or finding satisfying lighting conditions, in reality, is laborious and time-consuming, so it is of great value to develop a technology to manipulate illumination in an image as post-processing. Although previous works have explored techniques based on the physical viewpoint for relighting images, extensive supervisions and prior knowledge are necessary to generate reasonable images, restricting the generalization ability of these works. In contrast, we take the viewpoint of image-to-image translation and implicitly merge ideas of the conventional physical viewpoint. In this paper, we present an Illumination-Aware Network (IAN) which follows the guidance from hierarchical sampling to progressively relight a scene from a single image with high efficiency. In addition, an Illumination-Aware Residual Block (IARB) is designed to approximate the physical rendering process and to extract precise descriptors of light sources for further manipulations. We also introduce a depth-guided geometry encoder for acquiring valuable geometry- and structure-related representations once the depth information is available. Experimental results show that our proposed method produces better quantitative and qualitative relighting results than previous state-of-the-art methods. The code and models are publicly available on this https URL.

17.Unsupervised Night Image Enhancement: When Layer Decomposition Meets Light-Effects Suppression ⬇️

Night images suffer not only from low light, but also from uneven distributions of light. Most existing night visibility enhancement methods focus mainly on enhancing low-light regions. This inevitably leads to over enhancement and saturation in bright regions, such as those regions affected by light effects (glare, floodlight, etc). To address this problem, we need to suppress the light effects in bright regions while, at the same time, boosting the intensity of dark regions. With this idea in mind, we introduce an unsupervised method that integrates a layer decomposition network and a light-effects suppression network. Given a single night image as input, our decomposition network learns to decompose shading, reflectance and light-effects layers, guided by unsupervised layer-specific prior losses. Our light-effects suppression network further suppresses the light effects and, at the same time, enhances the illumination in dark regions. This light-effects suppression network exploits the estimated light-effects layer as the guidance to focus on the light-effects regions. To recover the background details and reduce hallucination/artefacts, we propose structure and high-frequency consistency losses. Our quantitative and qualitative evaluations on real images show that our method outperforms state-of-the-art methods in suppressing night light effects and boosting the intensity of dark regions.

18.Neural Network Learning of Chemical Bond Representations in Spectral Indices and Features ⬇️

In this paper we investigate neural networks for classification in hyperspectral imaging with a focus on connecting the architecture of the network with the physics of the sensing and materials present. Spectroscopy is the process of measuring light reflected or emitted by a material as a function wavelength. Molecular bonds present in the material have vibrational frequencies which affect the amount of light measured at each wavelength. Thus the measured spectrum contains information about the particular chemical constituents and types of bonds. For example, chlorophyll reflects more light in the near-IR rage (800-900nm) than in the red (625-675nm) range, and this difference can be measured using a normalized vegetation difference index (NDVI), which is commonly used to detect vegetation presence, health, and type in imagery collected at these wavelengths. In this paper we show that the weights in a Neural Network trained on different vegetation classes learn to measure this difference in reflectance. We then show that a Neural Network trained on a more complex set of ten different polymer materials will learn spectral 'features' evident in the weights for the network, and these features can be used to reliably distinguish between the different types of polymers. Examination of the weights provides a human-interpretable understanding of the network.

19.Real-Time Elderly Monitoring for Senior Safety by Lightweight Human Action Recognition ⬇️

With an increasing number of elders living alone, care-giving from a distance becomes a compelling need, particularly for safety. Real-time monitoring and action recognition are essential to raise an alert timely when abnormal behaviors or unusual activities occur. While wearable sensors are widely recognized as a promising solution, highly depending on user's ability and willingness makes them inefficient. In contrast, video streams collected through non-contact optical cameras provide richer information and release the burden on elders. In this paper, leveraging the Independently-Recurrent neural Network (IndRNN) we propose a novel Real-time Elderly Monitoring for senior Safety (REMS) based on lightweight human action recognition (HAR) technology. Using captured skeleton images, the REMS scheme is able to recognize abnormal behaviors or actions and preserve the user's privacy. To achieve high accuracy, the HAR module is trained and fine-tuned using multiple databases. An extensive experimental study verified that REMS system performs action recognition accurately and timely. REMS meets the design goals as a privacy-preserving elderly safety monitoring system and possesses the potential to be adopted in various smart monitoring systems.

20.Multi-modal Retinal Image Registration Using a Keypoint-Based Vessel Structure Aligning Network ⬇️

In ophthalmological imaging, multiple imaging systems, such as color fundus, infrared, fluorescein angiography, optical coherence tomography (OCT) or OCT angiography, are often involved to make a diagnosis of retinal disease. Multi-modal retinal registration techniques can assist ophthalmologists by providing a pixel-based comparison of aligned vessel structures in images from different modalities or acquisition times. To this end, we propose an end-to-end trainable deep learning method for multi-modal retinal image registration. Our method extracts convolutional features from the vessel structure for keypoint detection and description and uses a graph neural network for feature matching. The keypoint detection and description network and graph neural network are jointly trained in a self-supervised manner using synthetic multi-modal image pairs and are guided by synthetically sampled ground truth homographies. Our method demonstrates higher registration accuracy as competing methods for our synthetic retinal dataset and generalizes well for our real macula dataset and a public fundus dataset.

21.Towards Efficient Adversarial Training on Vision Transformers ⬇️

Vision Transformer (ViT), as a powerful alternative to Convolutional Neural Network (CNN), has received much attention. Recent work showed that ViTs are also vulnerable to adversarial examples like CNNs. To build robust ViTs, an intuitive way is to apply adversarial training since it has been shown as one of the most effective ways to accomplish robust CNNs. However, one major limitation of adversarial training is its heavy computational cost. The self-attention mechanism adopted by ViTs is a computationally intense operation whose expense increases quadratically with the number of input patches, making adversarial training on ViTs even more time-consuming. In this work, we first comprehensively study fast adversarial training on a variety of vision transformers and illustrate the relationship between the efficiency and robustness. Then, to expediate adversarial training on ViTs, we propose an efficient Attention Guided Adversarial Training mechanism. Specifically, relying on the specialty of self-attention, we actively remove certain patch embeddings of each layer with an attention-guided dropping strategy during adversarial training. The slimmed self-attention modules accelerate the adversarial training on ViTs significantly. With only 65% of the fast adversarial training time, we match the state-of-the-art results on the challenging ImageNet benchmark.

22.Multi-Event-Camera Depth Estimation and Outlier Rejection by Refocused Events Fusion ⬇️

Event cameras are bio-inspired sensors that offer advantages over traditional cameras. They work asynchronously, sampling the scene with microsecond resolution and producing a stream of brightness changes. This unconventional output has sparked novel computer vision methods to unlock the camera's potential. We tackle the problem of event-based stereo 3D reconstruction for SLAM. Most event-based stereo methods try to exploit the camera's high temporal resolution and event simultaneity across cameras to establish matches and estimate depth. By contrast, we investigate how to estimate depth without explicit data association by fusing Disparity Space Images (DSIs) originated in efficient monocular methods. We develop fusion theory and apply it to design multi-camera 3D reconstruction algorithms that produce state-of-the-art results, as we confirm by comparing against four baseline methods and testing on a variety of available datasets.

23.LPYOLO: Low Precision YOLO for Face Detection on FPGA ⬇️

In recent years, number of edge computing devices and artificial intelligence applications on them have advanced excessively. In edge computing, decision making processes and computations are moved from servers to edge devices. Hence, cheap and low power devices are required. FPGAs are very low power, inclined to do parallel operations and deeply suitable devices for running Convolutional Neural Networks (CNN) which are the fundamental unit of an artificial intelligence application. Face detection on surveillance systems is the most expected application on the security market. In this work, TinyYolov3 architecture is redesigned and deployed for face detection. It is a CNN based object detection method and developed for embedded systems. PYNQ-Z2 is selected as a target board which has low-end Xilinx Zynq 7020 System-on-Chip (SoC) on it. Redesigned TinyYolov3 model is defined in numerous bit width precisions with Brevitas library which brings fundamental CNN layers and activations in integer quantized form. Then, the model is trained in a quantized structure with WiderFace dataset. In order to decrease latency and power consumption, onchip memory of the FPGA is configured as a storage of whole network parameters and the last activation function is modified as rescaled HardTanh instead of Sigmoid. Also, high degree of parallelism is applied to logical resources of the FPGA. The model is converted to an HLS based application with using FINN framework and FINN-HLS library which includes the layer definitions in C++. Later, the model is synthesized and deployed. CPU of the SoC is employed with multithreading mechanism and responsible for preprocessing, postprocessing and TCP/IP streaming operations. Consequently, 2.4 Watt total board power consumption, 18 Frames-Per-Second (FPS) throughput and 0.757 mAP accuracy rate on Easy category of the WiderFace are achieved with 4 bits precision model.

24.Semantic-Aware Fine-Grained Correspondence ⬇️

Establishing visual correspondence across images is a challenging and essential task. Recently, an influx of self-supervised methods have been proposed to better learn representations for visual correspondence. However, we find that these methods often fail to leverage semantic information and over-rely on the matching of low-level features. In contrast, human vision is capable of distinguishing between distinct objects as a pretext to tracking. Inspired by this paradigm, we propose to learn semantic-aware fine-grained correspondence. Firstly, we demonstrate that semantic correspondence is implicitly available through a rich set of image-level self-supervised methods. We further design a pixel-level self-supervised learning objective which specifically targets fine-grained correspondence. For downstream tasks, we fuse these two kinds of complementary correspondence representations together, demonstrating that they boost performance synergistically. Our method surpasses previous state-of-the-art self-supervised methods using convolutional networks on a variety of visual correspondence tasks, including video object segmentation, human pose tracking, and human part tracking.

25.Magic ELF: Image Deraining Meets Association Learning and Transformer ⬇️

Convolutional neural network (CNN) and Transformer have achieved great success in multimedia applications. However, little effort has been made to effectively and efficiently harmonize these two architectures to satisfy image deraining. This paper aims to unify these two architectures to take advantage of their learning merits for image deraining. In particular, the local connectivity and translation equivariance of CNN and the global aggregation ability of self-attention (SA) in Transformer are fully exploited for specific local context and global structure representations. Based on the observation that rain distribution reveals the degradation location and degree, we introduce degradation prior to help background recovery and accordingly present the association refinement deraining scheme. A novel multi-input attention module (MAM) is proposed to associate rain perturbation removal and background recovery. Moreover, we equip our model with effective depth-wise separable convolutions to learn the specific feature representations and trade off computational complexity. Extensive experiments show that our proposed method (dubbed as ELF) outperforms the state-of-the-art approach (MPRNet) by 0.25 dB on average, but only accounts for 11.7% and 42.1% of its computational cost and parameters. The source code is available at this https URL.

26.An Efficient Spatio-Temporal Pyramid Transformer for Action Detection ⬇️

The task of action detection aims at deducing both the action category and localization of the start and end moment for each action instance in a long, untrimmed video. While vision Transformers have driven the recent advances in video understanding, it is non-trivial to design an efficient architecture for action detection due to the prohibitively expensive self-attentions over a long sequence of video clips. To this end, we present an efficient hierarchical Spatio-Temporal Pyramid Transformer (STPT) for action detection, building upon the fact that the early self-attention layers in Transformers still focus on local patterns. Specifically, we propose to use local window attention to encode rich local spatio-temporal representations in the early stages while applying global attention modules to capture long-term space-time dependencies in the later stages. In this way, our STPT can encode both locality and dependency with largely reduced redundancy, delivering a promising trade-off between accuracy and efficiency. For example, with only RGB input, the proposed STPT achieves 53.6% mAP on THUMOS14, surpassing I3D+AFSD RGB model by over 10% and performing favorably against state-of-the-art AFSD that uses additional flow features with 31% fewer GFLOPs, which serves as an effective and efficient end-to-end Transformer-based framework for action detection.

27.Weakly Supervised Object Localization via Transformer with Implicit Spatial Calibration ⬇️

Weakly Supervised Object Localization (WSOL), which aims to localize objects by only using image-level labels, has attracted much attention because of its low annotation cost in real applications. Recent studies leverage the advantage of self-attention in visual Transformer for long-range dependency to re-active semantic regions, aiming to avoid partial activation in traditional class activation mapping (CAM). However, the long-range modeling in Transformer neglects the inherent spatial coherence of the object, and it usually diffuses the semantic-aware regions far from the object boundary, making localization results significantly larger or far smaller. To address such an issue, we introduce a simple yet effective Spatial Calibration Module (SCM) for accurate WSOL, incorporating semantic similarities of patch tokens and their spatial relationships into a unified diffusion model. Specifically, we introduce a learnable parameter to dynamically adjust the semantic correlations and spatial context intensities for effective information propagation. In practice, SCM is designed as an external module of Transformer, and can be removed during inference to reduce the computation cost. The object-sensitive localization ability is implicitly embedded into the Transformer encoder through optimization in the training phase. It enables the generated attention maps to capture the sharper object boundaries and filter the object-irrelevant background area. Extensive experimental results demonstrate the effectiveness of the proposed method, which significantly outperforms its counterpart TS-CAM on both CUB-200 and ImageNet-1K benchmarks. The code is available at this https URL.

28.Mining Relations among Cross-Frame Affinities for Video Semantic Segmentation ⬇️

The essence of video semantic segmentation (VSS) is how to leverage temporal information for prediction. Previous efforts are mainly devoted to developing new techniques to calculate the cross-frame affinities such as optical flow and attention. Instead, this paper contributes from a different angle by mining relations among cross-frame affinities, upon which better temporal information aggregation could be achieved. We explore relations among affinities in two aspects: single-scale intrinsic correlations and multi-scale relations. Inspired by traditional feature processing, we propose Single-scale Affinity Refinement (SAR) and Multi-scale Affinity Aggregation (MAA). To make it feasible to execute MAA, we propose a Selective Token Masking (STM) strategy to select a subset of consistent reference tokens for different scales when calculating affinities, which also improves the efficiency of our method. At last, the cross-frame affinities strengthened by SAR and MAA are adopted for adaptively aggregating temporal information. Our experiments demonstrate that the proposed method performs favorably against state-of-the-art VSS methods. The code is publicly available at this https URL

29.Human Trajectory Prediction via Neural Social Physics ⬇️

Trajectory prediction has been widely pursued in many fields, and many model-based and model-free methods have been explored. The former include rule-based, geometric or optimization-based models, and the latter are mainly comprised of deep learning approaches. In this paper, we propose a new method combining both methodologies based on a new Neural Differential Equation model. Our new model (Neural Social Physics or NSP) is a deep neural network within which we use an explicit physics model with learnable parameters. The explicit physics model serves as a strong inductive bias in modeling pedestrian behaviors, while the rest of the network provides a strong data-fitting capability in terms of system parameter estimation and dynamics stochasticity modeling. We compare NSP with 15 recent deep learning methods on 6 datasets and improve the state-of-the-art performance by 5.56%-70%. Besides, we show that NSP has better generalizability in predicting plausible trajectories in drastically different scenarios where the density is 2-5 times as high as the testing data. Finally, we show that the physics model in NSP can provide plausible explanations for pedestrian behaviors, as opposed to black-box deep learning. Code is available: this https URL.

30.DC-ShadowNet: Single-Image Hard and Soft Shadow Removal Using Unsupervised Domain-Classifier Guided Network ⬇️

Shadow removal from a single image is generally still an open problem. Most existing learning-based methods use supervised learning and require a large number of paired images (shadow and corresponding non-shadow images) for training. A recent unsupervised method, Mask-ShadowGAN, addresses this limitation. However, it requires a binary mask to represent shadow regions, making it inapplicable to soft shadows. To address the problem, in this paper, we propose an unsupervised domain-classifier guided shadow removal network, DC-ShadowNet. Specifically, we propose to integrate a shadow/shadow-free domain classifier into a generator and its discriminator, enabling them to focus on shadow regions. To train our network, we introduce novel losses based on physics-based shadow-free chromaticity, shadow-robust perceptual features, and boundary smoothness. Moreover, we show that our unsupervised network can be used for test-time training that further improves the results. Our experiments show that all these novel components allow our method to handle soft shadows, and also to perform better on hard shadows both quantitatively and qualitatively than the existing state-of-the-art shadow removal methods.

31.StreamYOLO: Real-time Object Detection for Streaming Perception ⬇️

The perceptive models of autonomous driving require fast inference within a low latency for safety. While existing works ignore the inevitable environmental changes after processing, streaming perception jointly evaluates the latency and accuracy into a single metric for video online perception, guiding the previous works to search trade-offs between accuracy and speed. In this paper, we explore the performance of real time models on this metric and endow the models with the capacity of predicting the future, significantly improving the results for streaming perception. Specifically, we build a simple framework with two effective modules. One is a Dual Flow Perception module (DFP). It consists of dynamic flow and static flow in parallel to capture moving tendency and basic detection feature, respectively. Trend Aware Loss (TAL) is the other module which adaptively generates loss weight for each object with its moving speed. Realistically, we consider multiple velocities driving scene and further propose Velocity-awared streaming AP (VsAP) to jointly evaluate the accuracy. In this realistic setting, we design a efficient mix-velocity training strategy to guide detector perceive any velocities. Our simple method achieves the state-of-the-art performance on Argoverse-HD dataset and improves the sAP and VsAP by 4.7% and 8.2% respectively compared to the strong baseline, validating its effectiveness.

32.KD-MVS: Knowledge Distillation Based Self-supervised Learning for MVS ⬇️

Supervised multi-view stereo (MVS) methods have achieved remarkable progress in terms of reconstruction quality, but suffer from the challenge of collecting large-scale ground-truth depth. In this paper, we propose a novel self-supervised training pipeline for MVS based on knowledge distillation, termed \textit{KD-MVS}, which mainly consists of self-supervised teacher training and distillation-based student training. Specifically, the teacher model is trained in a self-supervised fashion using both photometric and featuremetric consistency. Then we distill the knowledge of the teacher model to the student model through probabilistic knowledge transferring. With the supervision of validated knowledge, the student model is able to outperform its teacher by a large margin. Extensive experiments performed on multiple datasets show our method can even outperform supervised methods.

33.Sequence Models for Drone vs Bird Classification ⬇️

Drone detection has become an essential task in object detection as drone costs have decreased and drone technology has improved. It is, however, difficult to detect distant drones when there is weak contrast, long range, and low visibility. In this work, we propose several sequence classification architectures to reduce the detected false-positive ratio of drone tracks. Moreover, we propose a new drone vs. bird sequence classification dataset to train and evaluate the proposed architectures. 3D CNN, LSTM, and Transformer based sequence classification architectures have been trained on the proposed dataset to show the effectiveness of the proposed idea. As experiments show, using sequence information, bird classification and overall F1 scores can be increased by up to 73% and 35%, respectively. Among all sequence classification models, R(2+1)D-based fully convolutional model yields the best transfer learning and fine-tuning results.

34.Semantic-aware Modular Capsule Routing for Visual Question Answering ⬇️

Visual Question Answering (VQA) is fundamentally compositional in nature, and many questions are simply answered by decomposing them into modular sub-problems. The recent proposed Neural Module Network (NMN) employ this strategy to question answering, whereas heavily rest with off-the-shelf layout parser or additional expert policy regarding the network architecture design instead of learning from the data. These strategies result in the unsatisfactory adaptability to the semantically-complicated variance of the inputs, thereby hindering the representational capacity and generalizability of the model. To tackle this problem, we propose a Semantic-aware modUlar caPsulE Routing framework, termed as SUPER, to better capture the instance-specific vision-semantic characteristics and refine the discriminative representations for prediction. Particularly, five powerful specialized modules as well as dynamic routers are tailored in each layer of the SUPER network, and the compact routing spaces are constructed such that a variety of customizable routes can be sufficiently exploited and the vision-semantic representations can be explicitly calibrated. We comparatively justify the effectiveness and generalization ability of our proposed SUPER scheme over five benchmark datasets, as well as the parametric-efficient advantage. It is worth emphasizing that this work is not to pursue the state-of-the-art results in VQA. Instead, we expect that our model is responsible to provide a novel perspective towards architecture learning and representation calibration for VQA.

35.Detecting Deepfake by Creating Spatio-Temporal Regularity Disruption ⬇️

Despite encouraging progress in deepfake detection, generalization to unseen forgery types remains a significant challenge due to the limited forgery clues explored during training. In contrast, we notice a common phenomenon in deepfake: fake video creation inevitably disrupts the statistical regularity in original videos. Inspired by this observation, we propose to boost the generalization of deepfake detection by distinguishing the "regularity disruption" that does not appear in real videos. Specifically, by carefully examining the spatial and temporal properties, we propose to disrupt a real video through a Pseudo-fake Generator and create a wide range of pseudo-fake videos for training. Such practice allows us to achieve deepfake detection without using fake videos and improves the generalization ability in a simple and efficient manner. To jointly capture the spatial and temporal disruptions, we propose a Spatio-Temporal Enhancement block to learn the regularity disruption across space and time on our self-created videos. Through comprehensive experiments, our method exhibits excellent performance on several datasets.

36.Correspondence Matters for Video Referring Expression Comprehension ⬇️

We investigate the problem of video Referring Expression Comprehension (REC), which aims to localize the referent objects described in the sentence to visual regions in the video frames. Despite the recent progress, existing methods suffer from two problems: 1) inconsistent localization results across video frames; 2) confusion between the referent and contextual objects. To this end, we propose a novel Dual Correspondence Network (dubbed as DCNet) which explicitly enhances the dense associations in both the inter-frame and cross-modal manners. Firstly, we aim to build the inter-frame correlations for all existing instances within the frames. Specifically, we compute the inter-frame patch-wise cosine similarity to estimate the dense alignment and then perform the inter-frame contrastive learning to map them close in feature space. Secondly, we propose to build the fine-grained patch-word alignment to associate each patch with certain words. Due to the lack of this kind of detailed annotations, we also predict the patch-word correspondence through the cosine similarity. Extensive experiments demonstrate that our DCNet achieves state-of-the-art performance on both video and image REC benchmarks. Furthermore, we conduct comprehensive ablation studies and thorough analyses to explore the optimal model designs. Notably, our inter-frame and cross-modal contrastive losses are plug-and-play functions and are applicable to any video REC architectures. For example, by building on top of Co-grounding, we boost the performance by 1.48% absolute improvement on Accu.@0.5 for VID-Sentence dataset.

37.D2-TPred: Discontinuous Dependency for Trajectory Prediction under Traffic Lights ⬇️

A profound understanding of inter-agent relationships and motion behaviors is important to achieve high-quality planning when navigating in complex scenarios, especially at urban traffic intersections. We present a trajectory prediction approach with respect to traffic lights, D2-TPred, which uses a spatial dynamic interaction graph (SDG) and a behavior dependency graph (BDG) to handle the problem of discontinuous dependency in the spatial-temporal space. Specifically, the SDG is used to capture spatial interactions by reconstructing sub-graphs for different agents with dynamic and changeable characteristics during each frame. The BDG is used to infer motion tendency by modeling the implicit dependency of the current state on priors behaviors, especially the discontinuous motions corresponding to acceleration, deceleration, or turning direction. Moreover, we present a new dataset for vehicle trajectory prediction under traffic lights called VTP-TL. Our experimental results show that our model achieves more than {20.45% and 20.78% }improvement in terms of ADE and FDE, respectively, on VTP-TL as compared to other trajectory prediction algorithms. The dataset and code are available at: this https URL.

38.Sobolev Training for Implicit Neural Representations with Approximated Image Derivatives ⬇️

Recently, Implicit Neural Representations (INRs) parameterized by neural networks have emerged as a powerful and promising tool to represent different kinds of signals due to its continuous, differentiable properties, showing superiorities to classical discretized representations. However, the training of neural networks for INRs only utilizes input-output pairs, and the derivatives of the target output with respect to the input, which can be accessed in some cases, are usually ignored. In this paper, we propose a training paradigm for INRs whose target output is image pixels, to encode image derivatives in addition to image values in the neural network. Specifically, we use finite differences to approximate image derivatives. We show how the training paradigm can be leveraged to solve typical INRs problems, i.e., image regression and inverse rendering, and demonstrate this training paradigm can improve the data-efficiency and generalization capabilities of INRs. The code of our method is available at \url{this https URL}.

39.FADE: Fusing the Assets of Decoder and Encoder for Task-Agnostic Upsampling ⬇️

We consider the problem of task-agnostic feature upsampling in dense prediction where an upsampling operator is required to facilitate both region-sensitive tasks like semantic segmentation and detail-sensitive tasks such as image matting. Existing upsampling operators often can work well in either type of the tasks, but not both. In this work, we present FADE, a novel, plug-and-play, and task-agnostic upsampling operator. FADE benefits from three design choices: i) considering encoder and decoder features jointly in upsampling kernel generation; ii) an efficient semi-shift convolutional operator that enables granular control over how each feature point contributes to upsampling kernels; iii) a decoder-dependent gating mechanism for enhanced detail delineation. We first study the upsampling properties of FADE on toy data and then evaluate it on large-scale semantic segmentation and image matting. In particular, FADE reveals its effectiveness and task-agnostic characteristic by consistently outperforming recent dynamic upsampling operators in different tasks. It also generalizes well across convolutional and transformer architectures with little computational overhead. Our work additionally provides thoughtful insights on what makes for task-agnostic upsampling. Code is available at: this http URL

40.Error Compensation Framework for Flow-Guided Video Inpainting ⬇️

The key to video inpainting is to use correlation information from as many reference frames as possible. Existing flow-based propagation methods split the video synthesis process into multiple steps: flow completion -> pixel propagation -> synthesis. However, there is a significant drawback that the errors in each step continue to accumulate and amplify in the next step. To this end, we propose an Error Compensation Framework for Flow-guided Video Inpainting (ECFVI), which takes advantage of the flow-based method and offsets its weaknesses. We address the weakness with the newly designed flow completion module and the error compensation network that exploits the error guidance map. Our approach greatly improves the temporal consistency and the visual quality of the completed videos. Experimental results show the superior performance of our proposed method with the speed up of x6, compared to the state-of-the-art methods. In addition, we present a new benchmark dataset for evaluation by supplementing the weaknesses of existing test datasets.

41.NSNet: Non-saliency Suppression Sampler for Efficient Video Recognition ⬇️

It is challenging for artificial intelligence systems to achieve accurate video recognition under the scenario of low computation costs. Adaptive inference based efficient video recognition methods typically preview videos and focus on salient parts to reduce computation costs. Most existing works focus on complex networks learning with video classification based objectives. Taking all frames as positive samples, few of them pay attention to the discrimination between positive samples (salient frames) and negative samples (non-salient frames) in supervisions. To fill this gap, in this paper, we propose a novel Non-saliency Suppression Network (NSNet), which effectively suppresses the responses of non-salient frames. Specifically, on the frame level, effective pseudo labels that can distinguish between salient and non-salient frames are generated to guide the frame saliency learning. On the video level, a temporal attention module is learned under dual video-level supervisions on both the salient and the non-salient representations. Saliency measurements from both two levels are combined for exploitation of multi-granularity complementary information. Extensive experiments conducted on four well-known benchmarks verify our NSNet not only achieves the state-of-the-art accuracy-efficiency trade-off but also present a significantly faster (2.4~4.3x) practical inference speed than state-of-the-art methods. Our project page is at this https URL .

42.Pose for Everything: Towards Category-Agnostic Pose Estimation ⬇️

Existing works on 2D pose estimation mainly focus on a certain category, e.g. human, animal, and vehicle. However, there are lots of application scenarios that require detecting the poses/keypoints of the unseen class of objects. In this paper, we introduce the task of Category-Agnostic Pose Estimation (CAPE), which aims to create a pose estimation model capable of detecting the pose of any class of object given only a few samples with keypoint definition. To achieve this goal, we formulate the pose estimation problem as a keypoint matching problem and design a novel CAPE framework, termed POse Matching Network (POMNet). A transformer-based Keypoint Interaction Module (KIM) is proposed to capture both the interactions among different keypoints and the relationship between the support and query images. We also introduce Multi-category Pose (MP-100) dataset, which is a 2D pose dataset of 100 object categories containing over 20K instances and is well-designed for developing CAPE algorithms. Experiments show that our method outperforms other baseline approaches by a large margin. Codes and data are available at this https URL.

43.Temporal Saliency Query Network for Efficient Video Recognition ⬇️

Efficient video recognition is a hot-spot research topic with the explosive growth of multimedia data on the Internet and mobile devices. Most existing methods select the salient frames without awareness of the class-specific saliency scores, which neglect the implicit association between the saliency of frames and its belonging category. To alleviate this issue, we devise a novel Temporal Saliency Query (TSQ) mechanism, which introduces class-specific information to provide fine-grained cues for saliency measurement. Specifically, we model the class-specific saliency measuring process as a query-response task. For each category, the common pattern of it is employed as a query and the most salient frames are responded to it. Then, the calculated similarities are adopted as the frame saliency scores. To achieve it, we propose a Temporal Saliency Query Network (TSQNet) that includes two instantiations of the TSQ mechanism based on visual appearance similarities and textual event-object relations. Afterward, cross-modality interactions are imposed to promote the information exchange between them. Finally, we use the class-specific saliencies of the most confident categories generated by two modalities to perform the selection of salient frames. Extensive experiments demonstrate the effectiveness of our method by achieving state-of-the-art results on ActivityNet, FCVID and Mini-Kinetics datasets. Our project page is at this https URL .

44.Land Classification in Satellite Images by Injecting Traditional Features to CNN Models ⬇️

Deep learning methods have been successfully applied to remote sensing problems for several years. Among these methods, CNN based models have high accuracy in solving the land classification problem using satellite or aerial images. Although these models have high accuracy, this generally comes with large memory size requirements. On the other hand, it is desirable to have small-sized models for applications, such as the ones implemented on unmanned aerial vehicles, with low memory space. Unfortunately, small-sized CNN models do not provide high accuracy as with their large-sized versions. In this study, we propose a novel method to improve the accuracy of CNN models, especially the ones with small size, by injecting traditional features to them. To test the effectiveness of the proposed method, we applied it to the CNN models SqueezeNet, MobileNetV2, ShuffleNetV2, VGG16, and ResNet50V2 having size 0.5 MB to 528 MB. We used the sample mean, gray level co-occurrence matrix features, Hu moments, local binary patterns, histogram of oriented gradients, and color invariants as traditional features for injection. We tested the proposed method on the EuroSAT dataset to perform land classification. Our experimental results show that the proposed method significantly improves the land classification accuracy especially when applied to small-sized CNN models.

45.LocVTP: Video-Text Pre-training for Temporal Localization ⬇️

Video-Text Pre-training (VTP) aims to learn transferable representations for various downstream tasks from large-scale web videos. To date, almost all existing VTP methods are limited to retrieval-based downstream tasks, e.g., video retrieval, whereas their transfer potentials on localization-based tasks, e.g., temporal grounding, are under-explored. In this paper, we experimentally analyze and demonstrate the incompatibility of current VTP methods with localization tasks, and propose a novel Localization-oriented Video-Text Pre-training framework, dubbed as LocVTP. Specifically, we perform the fine-grained contrastive alignment as a complement to the coarse-grained one by a clip-word correspondence discovery scheme. To further enhance the temporal reasoning ability of the learned feature, we propose a context projection head and a temporal aware contrastive loss to perceive the contextual relationships. Extensive experiments on four downstream tasks across six datasets demonstrate that our LocVTP achieves state-of-the-art performance on both retrieval-based and localization-based tasks. Furthermore, we conduct comprehensive ablation studies and thorough analyses to explore the optimum model designs and training strategies.

46.Learning from Data with Noisy Labels Using Temporal Self-Ensemble ⬇️

There are inevitably many mislabeled data in real-world datasets. Because deep neural networks (DNNs) have an enormous capacity to memorize noisy labels, a robust training scheme is required to prevent labeling errors from degrading the generalization performance of DNNs. Current state-of-the-art methods present a co-training scheme that trains dual networks using samples associated with small losses. In practice, however, training two networks simultaneously can burden computing resources. In this study, we propose a simple yet effective robust training scheme that operates by training only a single network. During training, the proposed method generates temporal self-ensemble by sampling intermediate network parameters from the weight trajectory formed by stochastic gradient descent optimization. The loss sum evaluated with these self-ensembles is used to identify incorrectly labeled samples. In parallel, our method generates multi-view predictions by transforming an input data into various forms and considers their agreement to identify incorrectly labeled samples. By combining the aforementioned metrics, we present the proposed {\it self-ensemble-based robust training} (SRT) method, which can filter the samples with noisy labels to reduce their influence on training. Experiments on widely-used public datasets demonstrate that the proposed method achieves a state-of-the-art performance in some categories without training the dual networks.

47.Auto Machine Learning for Medical Image Analysis by Unifying the Search on Data Augmentation and Neural Architecture ⬇️

Automated data augmentation, which aims at engineering augmentation policy automatically, recently draw a growing research interest. Many previous auto-augmentation methods utilized a Density Matching strategy by evaluating policies in terms of the test-time augmentation performance. In this paper, we theoretically and empirically demonstrated the inconsistency between the train and validation set of small-scale medical image datasets, referred to as in-domain sampling bias. Next, we demonstrated that the in-domain sampling bias might cause the inefficiency of Density Matching. To address the problem, an improved augmentation search strategy, named Augmented Density Matching, was proposed by randomly sampling policies from a prior distribution for training. Moreover, an efficient automatical machine learning(AutoML) algorithm was proposed by unifying the search on data augmentation and neural architecture. Experimental results indicated that the proposed methods outperformed state-of-the-art approaches on MedMNIST, a pioneering benchmark designed for AutoML in medical image analysis.

48.CADyQ: Content-Aware Dynamic Quantization for Image Super-Resolution ⬇️

Despite breakthrough advances in image super-resolution (SR) with convolutional neural networks (CNNs), SR has yet to enjoy ubiquitous applications due to the high computational complexity of SR networks. Quantization is one of the promising approaches to solve this problem. However, existing methods fail to quantize SR models with a bit-width lower than 8 bits, suffering from severe accuracy loss due to fixed bit-width quantization applied everywhere. In this work, to achieve high average bit-reduction with less accuracy loss, we propose a novel Content-Aware Dynamic Quantization (CADyQ) method for SR networks that allocates optimal bits to local regions and layers adaptively based on the local contents of an input image. To this end, a trainable bit selector module is introduced to determine the proper bit-width and quantization level for each layer and a given local image patch. This module is governed by the quantization sensitivity that is estimated by using both the average magnitude of image gradient of the patch and the standard deviation of the input feature of the layer. The proposed quantization pipeline has been tested on various SR networks and evaluated on several standard benchmarks extensively. Significant reduction in computational complexity and the elevated restoration accuracy clearly demonstrate the effectiveness of the proposed CADyQ framework for SR. Codes are available at this https URL.

49.UFO: Unified Feature Optimization ⬇️

This paper proposes a novel Unified Feature Optimization (UFO) paradigm for training and deploying deep models under real-world and large-scale scenarios, which requires a collection of multiple AI functions. UFO aims to benefit each single task with a large-scale pretraining on all tasks. Compared with the well known foundation model, UFO has two different points of emphasis, i.e., relatively smaller model size and NO adaptation cost: 1) UFO squeezes a wide range of tasks into a moderate-sized unified model in a multi-task learning manner and further trims the model size when transferred to down-stream tasks. 2) UFO does not emphasize transfer to novel tasks. Instead, it aims to make the trimmed model dedicated for one or more already-seen task. With these two characteristics, UFO provides great convenience for flexible deployment, while maintaining the benefits of large-scale pretraining. A key merit of UFO is that the trimming process not only reduces the model size and inference consumption, but also even improves the accuracy on certain tasks. Specifically, UFO considers the multi-task training and brings two-fold impact on the unified model: some closely related tasks have mutual benefits, while some tasks have conflicts against each other. UFO manages to reduce the conflicts and to preserve the mutual benefits through a novel Network Architecture Search (NAS) method. Experiments on a wide range of deep representation learning tasks (i.e., face recognition, person re-identification, vehicle re-identification and product retrieval) show that the model trimmed from UFO achieves higher accuracy than its single-task-trained counterpart and yet has smaller model size, validating the concept of UFO. Besides, UFO also supported the release of 17 billion parameters computer vision (CV) foundation model which is the largest CV model in the industry.

50.OIMNet++: Prototypical Normalization and Localization-aware Learning for Person Search ⬇️

We address the task of person search, that is, localizing and re-identifying query persons from a set of raw scene images. Recent approaches are typically built upon OIMNet, a pioneer work on person search, that learns joint person representations for performing both detection and person re-identification (reID) tasks. To obtain the representations, they extract features from pedestrian proposals, and then project them on a unit hypersphere with L2 normalization. These methods also incorporate all positive proposals, that sufficiently overlap with the ground truth, equally to learn person representations for reID. We have found that 1) the L2 normalization without considering feature distributions degenerates the discriminative power of person representations, and 2) positive proposals often also depict background clutter and person overlaps, which could encode noisy features to person representations. In this paper, we introduce OIMNet++ that addresses the aforementioned limitations. To this end, we introduce a novel normalization layer, dubbed ProtoNorm, that calibrates features from pedestrian proposals, while considering a long-tail distribution of person IDs, enabling L2 normalized person representations to be discriminative. We also propose a localization-aware feature learning scheme that encourages better-aligned proposals to contribute more in learning discriminative representations. Experimental results and analysis on standard person search benchmarks demonstrate the effectiveness of OIMNet++.

51.Efficient CNN Architecture Design Guided by Visualization ⬇️

Modern efficient Convolutional Neural Networks(CNNs) always use Depthwise Separable Convolutions(DSCs) and Neural Architecture Search(NAS) to reduce the number of parameters and the computational complexity. But some inherent characteristics of networks are overlooked. Inspired by visualizing feature maps and N$\times$N(N$>$1) convolution kernels, several guidelines are introduced in this paper to further improve parameter efficiency and inference speed. Based on these guidelines, our parameter-efficient CNN architecture, called \textit{VGNetG}, achieves better accuracy and lower latency than previous networks with about 30%$\thicksim$50% parameters reduction. Our VGNetG-1.0MP achieves 67.7% top-1 accuracy with 0.99M parameters and 69.2% top-1 accuracy with 1.14M parameters on ImageNet classification dataset.
Furthermore, we demonstrate that edge detectors can replace learnable depthwise convolution layers to mix features by replacing the N$\times$N kernels with fixed edge detection kernels. And our VGNetF-1.5MP archives 64.4%(-3.2%) top-1 accuracy and 66.2%(-1.4%) top-1 accuracy with additional Gaussian kernels.

52.AutoAlignV2: Deformable Feature Aggregation for Dynamic Multi-Modal 3D Object Detection ⬇️

Point clouds and RGB images are two general perceptional sources in autonomous driving. The former can provide accurate localization of objects, and the latter is denser and richer in semantic information. Recently, AutoAlign presents a learnable paradigm in combining these two modalities for 3D object detection. However, it suffers from high computational cost introduced by the global-wise attention. To solve the problem, we propose Cross-Domain DeformCAFA module in this work. It attends to sparse learnable sampling points for cross-modal relational modeling, which enhances the tolerance to calibration error and greatly speeds up the feature aggregation across different modalities. To overcome the complex GT-AUG under multi-modal settings, we design a simple yet effective cross-modal augmentation strategy on convex combination of image patches given their depth information. Moreover, by carrying out a novel image-level dropout training scheme, our model is able to infer in a dynamic manner. To this end, we propose AutoAlignV2, a faster and stronger multi-modal 3D detection framework, built on top of AutoAlign. Extensive experiments on nuScenes benchmark demonstrate the effectiveness and efficiency of AutoAlignV2. Notably, our best model reaches 72.4 NDS on nuScenes test leaderboard, achieving new state-of-the-art results among all published multi-modal 3D object detectors. Code will be available at this https URL.

53.SeedFormer: Patch Seeds based Point Cloud Completion with Upsample Transformer ⬇️

Point cloud completion has become increasingly popular among generation tasks of 3D point clouds, as it is a challenging yet indispensable problem to recover the complete shape of a 3D object from its partial observation. In this paper, we propose a novel SeedFormer to improve the ability of detail preservation and recovery in point cloud completion. Unlike previous methods based on a global feature vector, we introduce a new shape representation, namely Patch Seeds, which not only captures general structures from partial inputs but also preserves regional information of local patterns. Then, by integrating seed features into the generation process, we can recover faithful details for complete point clouds in a coarse-to-fine manner. Moreover, we devise an Upsample Transformer by extending the transformer structure into basic operations of point generators, which effectively incorporates spatial and semantic relationships between neighboring points. Qualitative and quantitative evaluations demonstrate that our method outperforms state-of-the-art completion networks on several benchmark datasets. Our code is available at this https URL.

54.Semi-Supervised Learning of Optical Flow by Flow Supervisor ⬇️

A training pipeline for optical flow CNNs consists of a pretraining stage on a synthetic dataset followed by a fine tuning stage on a target dataset. However, obtaining ground truth flows from a target video requires a tremendous effort. This paper proposes a practical fine tuning method to adapt a pretrained model to a target dataset without ground truth flows, which has not been explored extensively. Specifically, we propose a flow supervisor for self-supervision, which consists of parameter separation and a student output connection. This design is aimed at stable convergence and better accuracy over conventional self-supervision methods which are unstable on the fine tuning task. Experimental results show the effectiveness of our method compared to different self-supervision methods for semi-supervised learning. In addition, we achieve meaningful improvements over state-of-the-art optical flow models on Sintel and KITTI benchmarks by exploiting additional unlabeled datasets. Code is available at this https URL.

55.AdaNeRF: Adaptive Sampling for Real-time Rendering of Neural Radiance Fields ⬇️

Novel view synthesis has recently been revolutionized by learning neural radiance fields directly from sparse observations. However, rendering images with this new paradigm is slow due to the fact that an accurate quadrature of the volume rendering equation requires a large number of samples for each ray. Previous work has mainly focused on speeding up the network evaluations that are associated with each sample point, e.g., via caching of radiance values into explicit spatial data structures, but this comes at the expense of model compactness. In this paper, we propose a novel dual-network architecture that takes an orthogonal direction by learning how to best reduce the number of required sample points. To this end, we split our network into a sampling and shading network that are jointly trained. Our training scheme employs fixed sample positions along each ray, and incrementally introduces sparsity throughout training to achieve high quality even at low sample counts. After fine-tuning with the target number of samples, the resulting compact neural representation can be rendered in real-time. Our experiments demonstrate that our approach outperforms concurrent compact neural representations in terms of quality and frame rate and performs on par with highly efficient hybrid representations. Code and supplementary material is available at this https URL.

56.A Survey on Leveraging Pre-trained Generative Adversarial Networks for Image Editing and Restoration ⬇️

Generative adversarial networks (GANs) have drawn enormous attention due to the simple yet effective training mechanism and superior image generation quality. With the ability to generate photo-realistic high-resolution (e.g., $1024\times1024$) images, recent GAN models have greatly narrowed the gaps between the generated images and the real ones. Therefore, many recent works show emerging interest to take advantage of pre-trained GAN models by exploiting the well-disentangled latent space and the learned GAN priors. In this paper, we briefly review recent progress on leveraging pre-trained large-scale GAN models from three aspects, i.e., 1) the training of large-scale generative adversarial networks, 2) exploring and understanding the pre-trained GAN models, and 3) leveraging these models for subsequent tasks like image restoration and editing. More information about relevant methods and repositories can be found at this https URL.

57.On an Edge-Preserving Variational Model for Optical Flow Estimation ⬇️

It is well known that classical formulations resembling the Horn and Schunck model are still largely competitive due to the modern implementation practices. In most cases, these models outperform many modern flow estimation methods. In view of this, we propose an effective implementation design for an edge-preserving $L^1$ regularization approach to optical flow. The mathematical well-posedness of our proposed model is studied in the space of functions of bounded variations $BV(\Omega,\mathbb{R}^2)$. The implementation scheme is designed in multiple steps. The flow field is computed using the robust Chambolle-Pock primal-dual algorithm. Motivated by the recent studies of Castro and Donoho we extend the heuristic of iterated median filtering to our flow estimation. Further, to refine the flow edges we use the weighted median filter established by Li and Osher as a post-processing step. Our experiments on the Middlebury dataset show that the proposed method achieves the best average angular and end-point errors compared to some of the state-of-the-art Horn and Schunck based variational methods.

58.Learn From All: Erasing Attention Consistency for Noisy Label Facial Expression Recognition ⬇️

Noisy label Facial Expression Recognition (FER) is more challenging than traditional noisy label classification tasks due to the inter-class similarity and the annotation ambiguity. Recent works mainly tackle this problem by filtering out large-loss samples. In this paper, we explore dealing with noisy labels from a new feature-learning perspective. We find that FER models remember noisy samples by focusing on a part of the features that can be considered related to the noisy labels instead of learning from the whole features that lead to the latent truth. Inspired by that, we propose a novel Erasing Attention Consistency (EAC) method to suppress the noisy samples during the training process automatically. Specifically, we first utilize the flip semantic consistency of facial images to design an imbalanced framework. We then randomly erase input images and use flip attention consistency to prevent the model from focusing on a part of the features. EAC significantly outperforms state-of-the-art noisy label FER methods and generalizes well to other tasks with a large number of classes like CIFAR100 and Tiny-ImageNet. The code is available at this https URL.

59.Deep Learning for Unsupervised Anomaly Localization in Industrial Images: A Survey ⬇️

Currently, deep learning-based visual inspection has been highly successful with the help of supervised learning methods. However, in real industrial scenarios, the scarcity of defect samples, the cost of annotation, and the lack of a priori knowledge of defects may render supervised-based methods ineffective. In recent years, unsupervised anomaly localization algorithms have become more widely used in industrial inspection tasks. This paper aims to help researchers in this field by comprehensively surveying recent achievements in unsupervised anomaly localization in industrial images using deep learning. The survey reviews more than 120 significant publications covering different aspects of anomaly localization, mainly covering various concepts, challenges, taxonomies, benchmark datasets, and quantitative performance comparisons of the methods reviewed. In reviewing the achievements to date, this paper provides detailed predictions and analysis of several future research directions. This review provides detailed technical information for researchers interested in industrial anomaly localization and who wish to apply it to the localization of anomalies in other fields.

60.Multi-task Cross Attention Network in Facial Behavior Analysis ⬇️

Facial behavior analysis is a broad topic with various categories such as facial emotion recognition, age and gender recognition, ... Many studies focus on individual tasks while the multi-task learning approach is still open and requires more research. In this paper, we present our solution and experiment result for the Multi-Task Learning challenge of the Affective Behavior Analysis in-the-wild competition. The challenge is a combination of three tasks: action unit detection, facial expression recognition and valance-arousal estimation. To address this challenge, we introduce a cross-attentive module to improve multi-task learning performance. Additionally, a facial graph is applied to capture the association among action units. As a result, we achieve the evaluation measure of 1.24 on the validation data provided by the organizers, which is better than the baseline result of 0.30.

61.Image Generation Network for Covert Transmission in Online Social Network ⬇️

Online social networks have stimulated communications over the Internet more than ever, making it possible for secret message transmission over such noisy channels. In this paper, we propose a Coverless Image Steganography Network, called CIS-Net, that synthesizes a high-quality image directly conditioned on the secret message to transfer. CIS-Net is composed of four modules, namely, the Generation, Adversarial, Extraction, and Noise Module. The receiver can extract the hidden message without any loss even the images have been distorted by JPEG compression attacks. To disguise the behaviour of steganography, we collected images in the context of profile photos and stickers and train our network accordingly. As such, the generated images are more inclined to escape from malicious detection and attack. The distinctions from previous image steganography methods are majorly the robustness and losslessness against diverse attacks. Experiments over diverse public datasets have manifested the superior ability of anti-steganalysis.

62.AugRmixAT: A Data Processing and Training Method for Improving Multiple Robustness and Generalization Performance ⬇️

Deep neural networks are powerful, but they also have shortcomings such as their sensitivity to adversarial examples, noise, blur, occlusion, etc. Moreover, ensuring the reliability and robustness of deep neural network models is crucial for their application in safety-critical areas. Much previous work has been proposed to improve specific robustness. However, we find that the specific robustness is often improved at the sacrifice of the additional robustness or generalization ability of the neural network model. In particular, adversarial training methods significantly hurt the generalization performance on unperturbed data when improving adversarial robustness. In this paper, we propose a new data processing and training method, called AugRmixAT, which can simultaneously improve the generalization ability and multiple robustness of neural network models. Finally, we validate the effectiveness of AugRmixAT on the CIFAR-10/100 and Tiny-ImageNet datasets. The experiments demonstrate that AugRmixAT can improve the model's generalization performance while enhancing the white-box robustness, black-box robustness, common corruption robustness, and partial occlusion robustness.

63.Towards Accurate Open-Set Recognition via Background-Class Regularization ⬇️

In open-set recognition (OSR), classifiers should be able to reject unknown-class samples while maintaining high closed-set classification accuracy. To effectively solve the OSR problem, previous studies attempted to limit latent feature space and reject data located outside the limited space via offline analyses, e.g., distance-based feature analyses, or complicated network architectures. To conduct OSR via a simple inference process (without offline analyses) in standard classifier architectures, we use distance-based classifiers instead of conventional Softmax classifiers. Afterwards, we design a background-class regularization strategy, which uses background-class data as surrogates of unknown-class ones during training phase. Specifically, we formulate a novel regularization loss suitable for distance-based classifiers, which reserves sufficiently large class-wise latent feature spaces for known classes and forces background-class samples to be located far away from the limited spaces. Through our extensive experiments, we show that the proposed method provides robust OSR results, while maintaining high closed-set classification accuracy.

64.Grounding Visual Representations with Texts for Domain Generalization ⬇️

Reducing the representational discrepancy between source and target domains is a key component to maximize the model generalization. In this work, we advocate for leveraging natural language supervision for the domain generalization task. We introduce two modules to ground visual representations with texts containing typical reasoning of humans: (1) Visual and Textual Joint Embedder and (2) Textual Explanation Generator. The former learns the image-text joint embedding space where we can ground high-level class-discriminative information into the model. The latter leverages an explainable model and generates explanations justifying the rationale behind its decision. To the best of our knowledge, this is the first work to leverage the vision-and-language cross-modality approach for the domain generalization task. Our experiments with a newly created CUB-DG benchmark dataset demonstrate that cross-modality supervision can be successfully used to ground domain-invariant visual representations and improve the model generalization. Furthermore, in the large-scale DomainBed benchmark, our proposed method achieves state-of-the-art results and ranks 1st in average performance for five multi-domain datasets. The dataset and codes are available at this https URL.

65.Gradient-based Point Cloud Denoising with Uniformity ⬇️

Point clouds captured by depth sensors are often contaminated by noises, obstructing further analysis and applications. In this paper, we emphasize the importance of point distribution uniformity to downstream tasks. We demonstrate that point clouds produced by existing gradient-based denoisers lack uniformity despite having achieved promising quantitative results. To this end, we propose GPCD++, a gradient-based denoiser with an ultra-lightweight network named UniNet to address uniformity. Compared with previous state-of-the-art methods, our approach not only generates competitive or even better denoising results, but also significantly improves uniformity which largely benefits applications such as surface reconstruction.

66.Beyond single receptive field: A receptive field fusion-and-stratification network for airborne laser scanning point cloud classification ⬇️

The classification of airborne laser scanning (ALS) point clouds is a critical task of remote sensing and photogrammetry fields. Although recent deep learning-based methods have achieved satisfactory performance, they have ignored the unicity of the receptive field, which makes the ALS point cloud classification remain challenging for the distinguishment of the areas with complex structures and extreme scale variations. In this article, for the objective of configuring multi-receptive field features, we propose a novel receptive field fusion-and-stratification network (RFFS-Net). With a novel dilated graph convolution (DGConv) and its extension annular dilated convolution (ADConv) as basic building blocks, the receptive field fusion process is implemented with the dilated and annular graph fusion (DAGFusion) module, which obtains multi-receptive field feature representation through capturing dilated and annular graphs with various receptive regions. The stratification of the receptive fields with point sets of different resolutions as the calculation bases is performed with Multi-level Decoders nested in RFFS-Net and driven by the multi-level receptive field aggregation loss (MRFALoss) to drive the network to learn in the direction of the supervision labels with different resolutions. With receptive field fusion-and-stratification, RFFS-Net is more adaptable to the classification of regions with complex structures and extreme scale variations in large-scale ALS point clouds. Evaluated on the ISPRS Vaihingen 3D dataset, our RFFS-Net significantly outperforms the baseline approach by 5.3% on mF1 and 5.4% on mIoU, accomplishing an overall accuracy of 82.1%, an mF1 of 71.6%, and an mIoU of 58.2%. Furthermore, experiments on the LASDU dataset and the 2019 IEEE-GRSS Data Fusion Contest dataset show that RFFS-Net achieves a new state-of-the-art classification performance.

67.Don't Forget Me: Accurate Background Recovery for Text Removal via Modeling Local-Global Context ⬇️

Text removal has attracted increasingly attention due to its various applications on privacy protection, document restoration, and text editing. It has shown significant progress with deep neural network. However, most of the existing methods often generate inconsistent results for complex background. To address this issue, we propose a Contextual-guided Text Removal Network, termed as CTRNet. CTRNet explores both low-level structure and high-level discriminative context feature as prior knowledge to guide the process of background restoration. We further propose a Local-global Content Modeling (LGCM) block with CNNs and Transformer-Encoder to capture local features and establish the long-term relationship among pixels globally. Finally, we incorporate LGCM with context guidance for feature modeling and decoding. Experiments on benchmark datasets, SCUT-EnsText and SCUT-Syn show that CTRNet significantly outperforms the existing state-of-the-art methods. Furthermore, a qualitative experiment on examination papers also demonstrates the generalization ability of our method. The codes and supplement materials are available at this https URL.

68.DeltaGAN: Towards Diverse Few-shot Image Generation with Sample-Specific Delta ⬇️

Learning to generate new images for a novel category based on only a few images, named as few-shot image generation, has attracted increasing research interest. Several state-of-the-art works have yielded impressive results, but the diversity is still limited. In this work, we propose a novel Delta Generative Adversarial Network (DeltaGAN), which consists of a reconstruction subnetwork and a generation subnetwork. The reconstruction subnetwork captures intra-category transformation, i.e., delta, between same-category pairs. The generation subnetwork generates sample-specific delta for an input image, which is combined with this input image to generate a new image within the same category. Besides, an adversarial delta matching loss is designed to link the above two subnetworks together. Extensive experiments on six benchmark datasets demonstrate the effectiveness of our proposed method. Our code is available at this https URL.

69.Human-centric Image Cropping with Partition-aware and Content-preserving Features ⬇️

Image cropping aims to find visually appealing crops in an image, which is an important yet challenging task. In this paper, we consider a specific and practical application: human-centric image cropping, which focuses on the depiction of a person. To this end, we propose a human-centric image cropping method with two novel feature designs for the candidate crop: partition-aware feature and content-preserving feature. For partition-aware feature, we divide the whole image into nine partitions based on the human bounding box and treat different partitions in a candidate crop differently conditioned on the human information. For content-preserving feature, we predict a heatmap indicating the important content to be included in a good crop, and extract the geometric relation between the heatmap and a candidate crop. Extensive experiments demonstrate that our method can perform favorably against state-of-the-art image cropping methods on human-centric image cropping task. Code is available at this https URL.

70.Region Aware Video Object Segmentation with Deep Motion Modeling ⬇️

Current semi-supervised video object segmentation (VOS) methods usually leverage the entire features of one frame to predict object masks and update memory. This introduces significant redundant computations. To reduce redundancy, we present a Region Aware Video Object Segmentation (RAVOS) approach that predicts regions of interest (ROIs) for efficient object segmentation and memory storage. RAVOS includes a fast object motion tracker to predict their ROIs in the next frame. For efficient segmentation, object features are extracted according to the ROIs, and an object decoder is designed for object-level segmentation. For efficient memory storage, we propose motion path memory to filter out redundant context by memorizing the features within the motion path of objects between two frames. Besides RAVOS, we also propose a large-scale dataset, dubbed OVOS, to benchmark the performance of VOS models under occlusions. Evaluation on DAVIS and YouTube-VOS benchmarks and our new OVOS dataset show that our method achieves state-of-the-art performance with significantly faster inference time, e.g., 86.1 J&F at 42 FPS on DAVIS and 84.4 J&F at 23 FPS on YouTube-VOS.

71.Injecting 3D Perception of Controllable NeRF-GAN into StyleGAN for Editable Portrait Image Synthesis ⬇️

Over the years, 2D GANs have achieved great successes in photorealistic portrait generation. However, they lack 3D understanding in the generation process, thus they suffer from multi-view inconsistency problem. To alleviate the issue, many 3D-aware GANs have been proposed and shown notable results, but 3D GANs struggle with editing semantic attributes. The controllability and interpretability of 3D GANs have not been much explored. In this work, we propose two solutions to overcome these weaknesses of 2D GANs and 3D-aware GANs. We first introduce a novel 3D-aware GAN, SURF-GAN, which is capable of discovering semantic attributes during training and controlling them in an unsupervised manner. After that, we inject the prior of SURF-GAN into StyleGAN to obtain a high-fidelity 3D-controllable generator. Unlike existing latent-based methods allowing implicit pose control, the proposed 3D-controllable StyleGAN enables explicit pose control over portrait generation. This distillation allows direct compatibility between 3D control and many StyleGAN-based techniques (e.g., inversion and stylization), and also brings an advantage in terms of computational resources. Our codes are available at this https URL.

72.SGBANet: Semantic GAN and Balanced Attention Network for Arbitrarily Oriented Scene Text Recognition ⬇️

Scene text recognition is a challenging task due to the complex backgrounds and diverse variations of text instances. In this paper, we propose a novel Semantic GAN and Balanced Attention Network (SGBANet) to recognize the texts in scene images. The proposed method first generates the simple semantic feature using Semantic GAN and then recognizes the scene text with the Balanced Attention Module. The Semantic GAN aims to align the semantic feature distribution between the support domain and target domain. Different from the conventional image-to-image translation methods that perform at the image level, the Semantic GAN performs the generation and discrimination on the semantic level with the Semantic Generator Module (SGM) and Semantic Discriminator Module (SDM). For target images (scene text images), the Semantic Generator Module generates simple semantic features that share the same feature distribution with support images (clear text images). The Semantic Discriminator Module is used to distinguish the semantic features between the support domain and target domain. In addition, a Balanced Attention Module is designed to alleviate the problem of attention drift. The Balanced Attention Module first learns a balancing parameter based on the visual glimpse vector and semantic glimpse vector, and then performs the balancing operation for obtaining a balanced glimpse vector. Experiments on six benchmarks, including regular datasets, i.e., IIIT5K, SVT, ICDAR2013, and irregular datasets, i.e., ICDAR2015, SVTP, CUTE80, validate the effectiveness of our proposed method.

73.SplitMixer: Fat Trimmed From MLP-like Models ⬇️

We present SplitMixer, a simple and lightweight isotropic MLP-like architecture, for visual recognition. It contains two types of interleaving convolutional operations to mix information across spatial locations (spatial mixing) and channels (channel mixing). The first one includes sequentially applying two depthwise 1D kernels, instead of a 2D kernel, to mix spatial information. The second one is splitting the channels into overlapping or non-overlapping segments, with or without shared parameters, and applying our proposed channel mixing approaches or 3D convolution to mix channel information. Depending on design choices, a number of SplitMixer variants can be constructed to balance accuracy, the number of parameters, and speed. We show, both theoretically and experimentally, that SplitMixer performs on par with the state-of-the-art MLP-like models while having a significantly lower number of parameters and FLOPS. For example, without strong data augmentation and optimization, SplitMixer achieves around 94% accuracy on CIFAR-10 with only 0.28M parameters, while ConvMixer achieves the same accuracy with about 0.6M parameters. The well-known MLP-Mixer achieves 85.45% with 17.1M parameters. On CIFAR-100 dataset, SplitMixer achieves around 73% accuracy, on par with ConvMixer, but with about 52% fewer parameters and FLOPS. We hope that our results spark further research towards finding more efficient vision architectures and facilitate the development of MLP-like models. Code is available at this https URL.

74.GBDF: Gender Balanced DeepFake Dataset Towards Fair DeepFake Detection ⬇️

Facial forgery by deepfakes has raised severe societal concerns. Several solutions have been proposed by the vision community to effectively combat the misinformation on the internet via automated deepfake detection systems. Recent studies have demonstrated that facial analysis-based deep learning models can discriminate based on protected attributes. For the commercial adoption and massive roll-out of the deepfake detection technology, it is vital to evaluate and understand the fairness (the absence of any prejudice or favoritism) of deepfake detectors across demographic variations such as gender and race. As the performance differential of deepfake detectors between demographic subgroups would impact millions of people of the deprived sub-group. This paper aims to evaluate the fairness of the deepfake detectors across males and females. However, existing deepfake datasets are not annotated with demographic labels to facilitate fairness analysis. To this aim, we manually annotated existing popular deepfake datasets with gender labels and evaluated the performance differential of current deepfake detectors across gender. Our analysis on the gender-labeled version of the datasets suggests (a) current deepfake datasets have skewed distribution across gender, and (b) commonly adopted deepfake detectors obtain unequal performance across gender with mostly males outperforming females. Finally, we contributed a gender-balanced and annotated deepfake dataset, GBDF, to mitigate the performance differential and to promote research and development towards fairness-aware deep fake detectors. The GBDF dataset is publicly available at: this https URL

75.SPIN: An Empirical Evaluation on Sharing Parameters of Isotropic Networks ⬇️

Recent isotropic networks, such as ConvMixer and vision transformers, have found significant success across visual recognition tasks, matching or outperforming non-isotropic convolutional neural networks (CNNs). Isotropic architectures are particularly well-suited to cross-layer weight sharing, an effective neural network compression technique. In this paper, we perform an empirical evaluation on methods for sharing parameters in isotropic networks (SPIN). We present a framework to formalize major weight sharing design decisions and perform a comprehensive empirical evaluation of this design space. Guided by our experimental results, we propose a weight sharing strategy to generate a family of models with better overall efficiency, in terms of FLOPs and parameters versus accuracy, compared to traditional scaling methods alone, for example compressing ConvMixer by 1.9x while improving accuracy on ImageNet. Finally, we perform a qualitative study to further understand the behavior of weight sharing in isotropic architectures. The code is available at this https URL.

76.MeshMAE: Masked Autoencoders for 3D Mesh Data Analysis ⬇️

Recently, self-supervised pre-training has advanced Vision Transformers on various tasks w.r.t. different data modalities, e.g., image and 3D point cloud data. In this paper, we explore this learning paradigm for 3D mesh data analysis based on Transformers. Since applying Transformer architectures to new modalities is usually non-trivial, we first adapt Vision Transformer to 3D mesh data processing, i.e., Mesh Transformer. In specific, we divide a mesh into several non-overlapping local patches with each containing the same number of faces and use the 3D position of each patch's center point to form positional embeddings. Inspired by MAE, we explore how pre-training on 3D mesh data with the Transformer-based structure benefits downstream 3D mesh analysis tasks. We first randomly mask some patches of the mesh and feed the corrupted mesh into Mesh Transformers. Then, through reconstructing the information of masked patches, the network is capable of learning discriminative representations for mesh data. Therefore, we name our method MeshMAE, which can yield state-of-the-art or comparable performance on mesh analysis tasks, i.e., classification and segmentation. In addition, we also conduct comprehensive ablation studies to show the effectiveness of key designs in our method.

77.On Label Granularity and Object Localization ⬇️

Weakly supervised object localization (WSOL) aims to learn representations that encode object location using only image-level category labels. However, many objects can be labeled at different levels of granularity. Is it an animal, a bird, or a great horned owl? Which image-level labels should we use? In this paper we study the role of label granularity in WSOL. To facilitate this investigation we introduce iNatLoc500, a new large-scale fine-grained benchmark dataset for WSOL. Surprisingly, we find that choosing the right training label granularity provides a much larger performance boost than choosing the best WSOL algorithm. We also show that changing the label granularity can significantly improve data efficiency.

78.Spotting Temporally Precise, Fine-Grained Events in Video ⬇️

We introduce the task of spotting temporally precise, fine-grained events in video (detecting the precise moment in time events occur). Precise spotting requires models to reason globally about the full-time scale of actions and locally to identify subtle frame-to-frame appearance and motion differences that identify events during these actions. Surprisingly, we find that top performing solutions to prior video understanding tasks such as action detection and segmentation do not simultaneously meet both requirements. In response, we propose E2E-Spot, a compact, end-to-end model that performs well on the precise spotting task and can be trained quickly on a single GPU. We demonstrate that E2E-Spot significantly outperforms recent baselines adapted from the video action detection, segmentation, and spotting literature to the precise spotting task. Finally, we contribute new annotations and splits to several fine-grained sports action datasets to make these datasets suitable for future work on precise spotting.

79.On the Robustness of 3D Object Detectors ⬇️

In recent years, significant progress has been achieved for 3D object detection on point clouds thanks to the advances in 3D data collection and deep learning techniques. Nevertheless, 3D scenes exhibit a lot of variations and are prone to sensor inaccuracies as well as information loss during pre-processing. Thus, it is crucial to design techniques that are robust against these variations. This requires a detailed analysis and understanding of the effect of such variations. This work aims to analyze and benchmark popular point-based 3D object detectors against several data corruptions. To the best of our knowledge, we are the first to investigate the robustness of point-based 3D object detectors. To this end, we design and evaluate corruptions that involve data addition, reduction, and alteration. We further study the robustness of different modules against local and global variations. Our experimental results reveal several intriguing findings. For instance, we show that methods that integrate Transformers at a patch or object level lead to increased robustness, compared to using Transformers at the point level.

80.Hybrid CNN-Transformer Model For Facial Affect Recognition In the ABAW4 Challenge ⬇️

This paper describes our submission to the fourth Affective Behavior Analysis (ABAW) competition. We proposed a hybrid CNN-Transformer model for the Multi-Task-Learning (MTL) and Learning from Synthetic Data (LSD) task. Experimental results on validation dataset shows that our method achieves better performance than baseline model, which verifies that the effectiveness of proposed network.

81.Revisiting Hotels-50K and Hotel-ID ⬇️

In this paper, we propose revisited versions for two recent hotel recognition datasets: Hotels50K and Hotel-ID. The revisited versions provide evaluation setups with different levels of difficulty to better align with the intended real-world application, i.e. countering human trafficking. Real-world scenarios involve hotels and locations that are not captured in the current data sets, therefore it is important to consider evaluation settings where classes are truly unseen. We test this setup using multiple state-of-the-art image retrieval models and show that as expected, the models' performances decrease as the evaluation gets closer to the real-world unseen settings. The rankings of the best performing models also change across the different evaluation settings, which further motivates using the proposed revisited datasets.

82.2D GANs Meet Unsupervised Single-view 3D Reconstruction ⬇️

Recent research has shown that controllable image generation based on pre-trained GANs can benefit a wide range of computer vision tasks. However, less attention has been devoted to 3D vision tasks. In light of this, we propose a novel image-conditioned neural implicit field, which can leverage 2D supervisions from GAN-generated multi-view images and perform the single-view reconstruction of generic objects. Firstly, a novel offline StyleGAN-based generator is presented to generate plausible pseudo images with full control over the viewpoint. Then, we propose to utilize a neural implicit function, along with a differentiable renderer to learn 3D geometry from pseudo images with object masks and rough pose initializations. To further detect the unreliable supervisions, we introduce a novel uncertainty module to predict uncertainty maps, which remedy the negative effect of uncertain regions in pseudo images, leading to a better reconstruction performance. The effectiveness of our approach is demonstrated through superior single-view 3D reconstruction results of generic objects.

83.Controllable and Guided Face Synthesis for Unconstrained Face Recognition ⬇️

Although significant advances have been made in face recognition (FR), FR in unconstrained environments remains challenging due to the domain gap between the semi-constrained training datasets and unconstrained testing scenarios. To address this problem, we propose a controllable face synthesis model (CFSM) that can mimic the distribution of target datasets in a style latent space. CFSM learns a linear subspace with orthogonal bases in the style latent space with precise control over the diversity and degree of synthesis. Furthermore, the pre-trained synthesis model can be guided by the FR model, making the resulting images more beneficial for FR model training. Besides, target dataset distributions are characterized by the learned orthogonal bases, which can be utilized to measure the distributional similarity among face datasets. Our approach yields significant performance gains on unconstrained benchmarks, such as IJB-B, IJB-C, TinyFace and IJB-S (+5.76% Rank1).

84.Scene Recognition with Objectness, Attribute and Category Learning ⬇️

Scene classification has established itself as a challenging research problem. Compared to images of individual objects, scene images could be much more semantically complex and abstract. Their difference mainly lies in the level of granularity of recognition. Yet, image recognition serves as a key pillar for the good performance of scene recognition as the knowledge attained from object images can be used for accurate recognition of scenes. The existing scene recognition methods only take the category label of the scene into consideration. However, we find that the contextual information that contains detailed local descriptions are also beneficial in allowing the scene recognition model to be more discriminative. In this paper, we aim to improve scene recognition using attribute and category label information encoded in objects. Based on the complementarity of attribute and category labels, we propose a Multi-task Attribute-Scene Recognition (MASR) network which learns a category embedding and at the same time predicts scene attributes. Attribute acquisition and object annotation are tedious and time consuming tasks. We tackle the problem by proposing a partially supervised annotation strategy in which human intervention is significantly reduced. The strategy provides a much more cost-effective solution to real world scenarios, and requires considerably less annotation efforts. Moreover, we re-weight the attribute predictions considering the level of importance indicated by the object detected scores. Using the proposed method, we efficiently annotate attribute labels for four large-scale datasets, and systematically investigate how scene and attribute recognition benefit from each other. The experimental results demonstrate that MASR learns a more discriminative representation and achieves competitive recognition performance compared to the state-of-the-art methods

85.Video Anomaly Detection by Solving Decoupled Spatio-Temporal Jigsaw Puzzles ⬇️

Video Anomaly Detection (VAD) is an important topic in computer vision. Motivated by the recent advances in self-supervised learning, this paper addresses VAD by solving an intuitive yet challenging pretext task, i.e., spatio-temporal jigsaw puzzles, which is cast as a multi-label fine-grained classification problem. Our method exhibits several advantages over existing works: 1) the spatio-temporal jigsaw puzzles are decoupled in terms of spatial and temporal dimensions, responsible for capturing highly discriminative appearance and motion features, respectively; 2) full permutations are used to provide abundant jigsaw puzzles covering various difficulty levels, allowing the network to distinguish subtle spatio-temporal differences between normal and abnormal events; and 3) the pretext task is tackled in an end-to-end manner without relying on any pre-trained models. Our method outperforms state-of-the-art counterparts on three public benchmarks. Especially on ShanghaiTech Campus, the result is superior to reconstruction and prediction-based methods by a large margin.

86.Pediatric Bone Age Assessment using Deep Learning Models ⬇️

Bone age assessment (BAA) is a standard method for determining the age difference between skeletal and chronological age. Manual processes are complicated and necessitate the expertise of experts. This is where deep learning comes into play. In this study, pre-trained models like VGG-16, InceptionV3, XceptionNet, and MobileNet are used to assess the bone age of the input data, and their mean average errors are compared and evaluated to see which model predicts the best.

87.GOCA: Guided Online Cluster Assignment for Self-Supervised Video Representation Learning ⬇️

Clustering is a ubiquitous tool in unsupervised learning. Most of the existing self-supervised representation learning methods typically cluster samples based on visually dominant features. While this works well for image-based self-supervision, it often fails for videos, which require understanding motion rather than focusing on background. Using optical flow as complementary information to RGB can alleviate this problem. However, we observe that a naive combination of the two views does not provide meaningful gains. In this paper, we propose a principled way to combine two views. Specifically, we propose a novel clustering strategy where we use the initial cluster assignment of each view as prior to guide the final cluster assignment of the other view. This idea will enforce similar cluster structures for both views, and the formed clusters will be semantically abstract and robust to noisy inputs coming from each individual view. Additionally, we propose a novel regularization strategy to address the feature collapse problem, which is common in cluster-based self-supervised learning methods. Our extensive evaluation shows the effectiveness of our learned representations on downstream tasks, e.g., video retrieval and action recognition. Specifically, we outperform the state of the art by 7% on UCF and 4% on HMDB for video retrieval, and 5% on UCF and 6% on HMDB for video classification

88.Visual Knowledge Tracing ⬇️

Each year, thousands of people learn new visual categorization tasks -- radiologists learn to recognize tumors, birdwatchers learn to distinguish similar species, and crowd workers learn how to annotate valuable data for applications like autonomous driving. As humans learn, their brain updates the visual features it extracts and attend to, which ultimately informs their final classification decisions. In this work, we propose a novel task of tracing the evolving classification behavior of human learners as they engage in challenging visual classification tasks. We propose models that jointly extract the visual features used by learners as well as predicting the classification functions they utilize. We collect three challenging new datasets from real human learners in order to evaluate the performance of different visual knowledge tracing methods. Our results show that our recurrent models are able to predict the classification behavior of human learners on three challenging medical image and species identification tasks.

89.Analysis of the Effect of Low-Overhead Lossy Image Compression on the Performance of Visual Crowd Counting for Smart City Applications ⬇️

Images and video frames captured by cameras placed throughout smart cities are often transmitted over the network to a server to be processed by deep neural networks for various tasks. Transmission of raw images, i.e., without any form of compression, requires high bandwidth and can lead to congestion issues and delays in transmission. The use of lossy image compression techniques can reduce the quality of the images, leading to accuracy degradation. In this paper, we analyze the effect of applying low-overhead lossy image compression methods on the accuracy of visual crowd counting, and measure the trade-off between bandwidth reduction and the obtained accuracy.

90.Tackling Long-Tailed Category Distribution Under Domain Shifts ⬇️

Machine learning models fail to perform well on real-world applications when 1) the category distribution P(Y) of the training dataset suffers from long-tailed distribution and 2) the test data is drawn from different conditional distributions P(X|Y). Existing approaches cannot handle the scenario where both issues exist, which however is common for real-world applications. In this study, we took a step forward and looked into the problem of long-tailed classification under domain shifts. We designed three novel core functional blocks including Distribution Calibrated Classification Loss, Visual-Semantic Mapping and Semantic-Similarity Guided Augmentation. Furthermore, we adopted a meta-learning framework which integrates these three blocks to improve domain generalization on unseen target domains. Two new datasets were proposed for this problem, named AWA2-LTS and ImageNet-LTS. We evaluated our method on the two datasets and extensive experimental results demonstrate that our proposed method can achieve superior performance over state-of-the-art long-tailed/domain generalization approaches and the combinations. Source codes and datasets can be found at our project page https://xiaogu.site/LTDS.

91.A Generalized & Robust Framework For Timestamp Supervision in Temporal Action Segmentation ⬇️

In temporal action segmentation, Timestamp supervision requires only a handful of labelled frames per video sequence. For unlabelled frames, previous works rely on assigning hard labels, and performance rapidly collapses under subtle violations of the annotation assumptions. We propose a novel Expectation-Maximization (EM) based approach that leverages the label uncertainty of unlabelled frames and is robust enough to accommodate possible annotation errors. With accurate timestamp annotations, our proposed method produces SOTA results and even exceeds the fully-supervised setup in several metrics and datasets. When applied to timestamp annotations with missing action segments, our method presents stable performance. To further test our formulation's robustness, we introduce the new challenging annotation setup of Skip-tag supervision. This setup relaxes constraints and requires annotations of any fixed number of random frames in a video, making it more flexible than Timestamp supervision while remaining competitive.

92.Latent Discriminant deterministic Uncertainty ⬇️

Predictive uncertainty estimation is essential for deploying Deep Neural Networks in real-world autonomous systems. However, most successful approaches are computationally intensive. In this work, we attempt to address these challenges in the context of autonomous driving perception tasks. Recently proposed Deterministic Uncertainty Methods (DUM) can only partially meet such requirements as their scalability to complex computer vision tasks is not obvious. In this work we advance a scalable and effective DUM for high-resolution semantic segmentation, that relaxes the Lipschitz constraint typically hindering practicality of such architectures. We learn a discriminant latent space by leveraging a distinction maximization layer over an arbitrarily-sized set of trainable prototypes. Our approach achieves competitive results over Deep Ensembles, the state-of-the-art for uncertainty prediction, on image classification, segmentation and monocular depth estimation tasks. Our code is available at this https URL

93.Animation from Blur: Multi-modal Blur Decomposition with Motion Guidance ⬇️

We study the challenging problem of recovering detailed motion from a single motion-blurred image. Existing solutions to this problem estimate a single image sequence without considering the motion ambiguity for each region. Therefore, the results tend to converge to the mean of the multi-modal possibilities. In this paper, we explicitly account for such motion ambiguity, allowing us to generate multiple plausible solutions all in sharp detail. The key idea is to introduce a motion guidance representation, which is a compact quantization of 2D optical flow with only four discrete motion directions. Conditioned on the motion guidance, the blur decomposition is led to a specific, unambiguous solution by using a novel two-stage decomposition network. We propose a unified framework for blur decomposition, which supports various interfaces for generating our motion guidance, including human input, motion information from adjacent video frames, and learning from a video dataset. Extensive experiments on synthesized datasets and real-world data show that the proposed framework is qualitatively and quantitatively superior to previous methods, and also offers the merit of producing physically plausible and diverse solutions. Code is available at this https URL.

94.BRACE: The Breakdancing Competition Dataset for Dance Motion Synthesis ⬇️

Generative models for audio-conditioned dance motion synthesis map music features to dance movements. Models are trained to associate motion patterns to audio patterns, usually without an explicit knowledge of the human body. This approach relies on a few assumptions: strong music-dance correlation, controlled motion data and relatively simple poses and movements. These characteristics are found in all existing datasets for dance motion synthesis, and indeed recent methods can achieve good results.We introduce a new dataset aiming to challenge these common assumptions, compiling a set of dynamic dance sequences displaying complex human poses. We focus on breakdancing which features acrobatic moves and tangled postures. We source our data from the Red Bull BC One competition videos. Estimating human keypoints from these videos is difficult due to the complexity of the dance, as well as the multiple moving cameras recording setup. We adopt a hybrid labelling pipeline leveraging deep estimation models as well as manual annotations to obtain good quality keypoint sequences at a reduced cost. Our efforts produced the BRACE dataset, which contains over 3 hours and 30 minutes of densely annotated poses. We test state-of-the-art methods on BRACE, showing their limitations when evaluated on complex sequences. Our dataset can readily foster advance in dance motion synthesis. With intricate poses and swift movements, models are forced to go beyond learning a mapping between modalities and reason more effectively about body structure and movements.

95.Face-to-Face Co-Located Human-Human Social Interaction Analysis using Nonverbal Cues: A Survey ⬇️

This work presents a systematic review of recent efforts (since 2010) aimed at automatic analysis of nonverbal cues displayed in face-to-face co-located human-human social interactions. The main reason for focusing on nonverbal cues is that these are the physical, machine detectable traces of social and psychological phenomena. Therefore, detecting and understanding nonverbal cues means, at least to a certain extent, to detect and understand social and psychological phenomena. The covered topics are categorized into three as: a) modeling social traits, such as leadership, dominance, personality traits, b) social role recognition and social relations detection and c) interaction dynamics analysis in terms of group cohesion, empathy, rapport and so forth. We target the co-located interactions, in which the interactants are always humans. The survey covers a wide spectrum of settings and scenarios, including free-standing interactions, meetings, indoor and outdoor social exchanges, dyadic conversations, and crowd dynamics. For each of them, the survey considers the three main elements of nonverbal cues analysis, namely data, sensing approaches and computational methodologies. The goal is to highlight the main advances of the last decade, to point out existing limitations, and to outline future directions.

96.The MABe22 Benchmarks for Representation Learning of Multi-Agent Behavior ⬇️

Real-world behavior is often shaped by complex interactions between multiple agents. To scalably study multi-agent behavior, advances in unsupervised and self-supervised learning have enabled a variety of different behavioral representations to be learned from trajectory data. To date, there does not exist a unified set of benchmarks that can enable comparing methods quantitatively and systematically across a broad set of behavior analysis settings. We aim to address this by introducing a large-scale, multi-agent trajectory dataset from real-world behavioral neuroscience experiments that covers a range of behavior analysis tasks. Our dataset consists of trajectory data from common model organisms, with 9.6 million frames of mouse data and 4.4 million frames of fly data, in a variety of experimental settings, such as different strains, lengths of interaction, and optogenetic stimulation. A subset of the frames also consist of expert-annotated behavior labels. Improvements on our dataset corresponds to behavioral representations that work across multiple organisms and is able to capture differences for common behavior analysis tasks.

97.A Primer on Topological Data Analysis to Support Image Analysis Tasks in Environmental Science ⬇️

Topological data analysis (TDA) is a tool from data science and mathematics that is beginning to make waves in environmental science. In this work, we seek to provide an intuitive and understandable introduction to a tool from TDA that is particularly useful for the analysis of imagery, namely persistent homology. We briefly discuss the theoretical background but focus primarily on understanding the output of this tool and discussing what information it can glean. To this end, we frame our discussion around a guiding example of classifying satellite images from the Sugar, Fish, Flower, and Gravel Dataset produced for the study of mesocale organization of clouds by Rasp et. al. in 2020 (arXiv:1906:01906). We demonstrate how persistent homology and its vectorization, persistence landscapes, can be used in a workflow with a simple machine learning algorithm to obtain good results, and explore in detail how we can explain this behavior in terms of image-level features. One of the core strengths of persistent homology is how interpretable it can be, so throughout this paper we discuss not just the patterns we find, but why those results are to be expected given what we know about the theory of persistent homology. Our goal is that a reader of this paper will leave with a better understanding of TDA and persistent homology, be able to identify problems and datasets of their own for which persistent homology could be helpful, and gain an understanding of results they obtain from applying the included GitHub example code.

98.Online Localisation and Colored Mesh Reconstruction Architecture for 3D Visual Feedback in Robotic Exploration Missions ⬇️

This paper introduces an Online Localisation and Colored Mesh Reconstruction (OLCMR) ROS perception architecture for ground exploration robots aiming to perform robust Simultaneous Localisation And Mapping (SLAM) in challenging unknown environments and provide an associated colored 3D mesh representation in real time. It is intended to be used by a remote human operator to easily visualise the mapped environment during or after the mission or as a development base for further researches in the field of exploration robotics. The architecture is mainly composed of carefully-selected open-source ROS implementations of a LiDAR-based SLAM algorithm alongside a colored surface reconstruction procedure using a point cloud and RGB camera images projected into the 3D space. The overall performances are evaluated on the Newer College handheld LiDAR-Vision reference dataset and on two experimental trajectories gathered on board of representative wheeled robots in respectively urban and countryside outdoor environments. Index Terms: Field Robots, Mapping, SLAM, Colored Surface Reconstruction

99.Towards Confident Detection of Prostate Cancer using High Resolution Micro-ultrasound ⬇️

MOTIVATION: Detection of prostate cancer during transrectal ultrasound-guided biopsy is challenging. The highly heterogeneous appearance of cancer, presence of ultrasound artefacts, and noise all contribute to these difficulties. Recent advancements in high-frequency ultrasound imaging - micro-ultrasound - have drastically increased the capability of tissue imaging at high resolution. Our aim is to investigate the development of a robust deep learning model specifically for micro-ultrasound-guided prostate cancer biopsy. For the model to be clinically adopted, a key challenge is to design a solution that can confidently identify the cancer, while learning from coarse histopathology measurements of biopsy samples that introduce weak labels. METHODS: We use a dataset of micro-ultrasound images acquired from 194 patients, who underwent prostate biopsy. We train a deep model using a co-teaching paradigm to handle noise in labels, together with an evidential deep learning method for uncertainty estimation. We evaluate the performance of our model using the clinically relevant metric of accuracy vs. confidence. RESULTS: Our model achieves a well-calibrated estimation of predictive uncertainty with area under the curve of 88$%$. The use of co-teaching and evidential deep learning in combination yields significantly better uncertainty estimation than either alone. We also provide a detailed comparison against state-of-the-art in uncertainty estimation.

100.Fast Data Driven Estimation of Cluster Number in Multiplex Images using Embedded Density Outliers ⬇️

The usage of chemical imaging technologies is becoming a routine accompaniment to traditional methods in pathology. Significant technological advances have developed these next generation techniques to provide rich, spatially resolved, multidimensional chemical images. The rise of digital pathology has significantly enhanced the synergy of these imaging modalities with optical microscopy and immunohistochemistry, enhancing our understanding of the biological mechanisms and progression of diseases. Techniques such as imaging mass cytometry provide labelled multidimensional (multiplex) images of specific components used in conjunction with digital pathology techniques. These powerful techniques generate a wealth of high dimensional data that create significant challenges in data analysis. Unsupervised methods such as clustering are an attractive way to analyse these data, however, they require the selection of parameters such as the number of clusters. Here we propose a methodology to estimate the number of clusters in an automatic data-driven manner using a deep sparse autoencoder to embed the data into a lower dimensional space. We compute the density of regions in the embedded space, the majority of which are empty, enabling the high density regions to be detected as outliers and provide an estimate for the number of clusters. This framework provides a fully unsupervised and data-driven method to analyse multidimensional data. In this work we demonstrate our method using 45 multiplex imaging mass cytometry datasets. Moreover, our model is trained using only one of the datasets and the learned embedding is applied to the remaining 44 images providing an efficient process for data analysis. Finally, we demonstrate the high computational efficiency of our method which is two orders of magnitude faster than estimating via computing the sum squared distances as a function of cluster number.

101.COBRA: Cpu-Only aBdominal oRgan segmentAtion ⬇️

Abdominal organ segmentation is a difficult and time-consuming task. To reduce the burden on clinical experts, fully-automated methods are highly desirable. Current approaches are dominated by Convolutional Neural Networks (CNNs) however the computational requirements and the need for large data sets limit their application in practice. By implementing a small and efficient custom 3D CNN, compiling the trained model and optimizing the computational graph: our approach produces high accuracy segmentations (Dice Similarity Coefficient (%): Liver: 97.3$\pm$1.3, Kidneys: 94.8$\pm$3.6, Spleen: 96.4$\pm$3.0, Pancreas: 80.9$\pm$10.1) at a rate of 1.6 seconds per image. Crucially, we are able to perform segmentation inference solely on CPU (no GPU required), thereby facilitating easy and widespread deployment of the model without specialist hardware.

102.Improved Generative Model for Weakly Supervised Chest Anomaly Localization via Pseudo-paired Registration with Bilaterally Symmetrical Data Augmentation ⬇️

Image translation based on a generative adversarial network (GAN-IT) is a promising method for precise localization of abnormal regions in chest X-ray images (AL-CXR). However, heterogeneous unpaired datasets undermine existing methods to extract key features and distinguish normal from abnormal cases, resulting in inaccurate and unstable AL-CXR. To address this problem, we propose an improved two-stage GAN-IT involving registration and data augmentation. For the first stage, we introduce an invertible deep-learning-based registration technique that virtually and reasonably converts unpaired data into paired data for learning registration maps. This novel approach achieves high registration performance. For the second stage, we apply data augmentation to diversify anomaly locations by swapping the left and right lung regions on the uniform registered frames, further improving the performance by alleviating imbalance in data distribution showing left and right lung lesions. Our method is intended for application to existing GAN-IT models, allowing existing architecture to benefit from key features for translation. By showing that the AL-CXR performance is uniformly improved when applying the proposed method, we believe that GAN-IT for AL-CXR can be deployed in clinical environments, even if learning data are scarce.

103.Bitwidth-Adaptive Quantization-Aware Neural Network Training: A Meta-Learning Approach ⬇️

Deep neural network quantization with adaptive bitwidths has gained increasing attention due to the ease of model deployment on various platforms with different resource budgets. In this paper, we propose a meta-learning approach to achieve this goal. Specifically, we propose MEBQAT, a simple yet effective way of bitwidth-adaptive quantization aware training (QAT) where meta-learning is effectively combined with QAT by redefining meta-learning tasks to incorporate bitwidths. After being deployed on a platform, MEBQAT allows the (meta-)trained model to be quantized to any candidate bitwidth then helps to conduct inference without much accuracy drop from quantization. Moreover, with a few-shot learning scenario, MEBQAT can also adapt a model to any bitwidth as well as any unseen target classes by adding conventional optimization or metric-based meta-learning. We design variants of MEBQAT to support both (1) a bitwidth-adaptive quantization scenario and (2) a new few-shot learning scenario where both quantization bitwidths and target classes are jointly adapted. We experimentally demonstrate their validity in multiple QAT schemes. By comparing their performance to (bitwidth-dedicated) QAT, existing bitwidth adaptive QAT and vanilla meta-learning, we find that merging bitwidths into meta-learning tasks achieves a higher level of robustness.

104.Flow-based Visual Quality Enhancer for Super-resolution Magnetic Resonance Spectroscopic Imaging ⬇️

Magnetic Resonance Spectroscopic Imaging (MRSI) is an essential tool for quantifying metabolites in the body, but the low spatial resolution limits its clinical applications. Deep learning-based super-resolution methods provided promising results for improving the spatial resolution of MRSI, but the super-resolved images are often blurry compared to the experimentally-acquired high-resolution images. Attempts have been made with the generative adversarial networks to improve the image visual quality. In this work, we consider another type of generative model, the flow-based model, of which the training is more stable and interpretable compared to the adversarial networks. Specifically, we propose a flow-based enhancer network to improve the visual quality of super-resolution MRSI. Different from previous flow-based models, our enhancer network incorporates anatomical information from additional image modalities (MRI) and uses a learnable base distribution. In addition, we impose a guide loss and a data-consistency loss to encourage the network to generate images with high visual quality while maintaining high fidelity. Experiments on a 1H-MRSI dataset acquired from 25 high-grade glioma patients indicate that our enhancer network outperforms the adversarial networks and the baseline flow-based methods. Our method also allows visual quality adjustment and uncertainty estimation.

105.Liver Segmentation using Turbolift Learning for CT and Cone-beam C-arm Perfusion Imaging ⬇️

Model-based reconstruction employing the time separation technique (TST) was found to improve dynamic perfusion imaging of the liver using C-arm cone-beam computed tomography (CBCT). To apply TST using prior knowledge extracted from CT perfusion data, the liver should be accurately segmented from the CT scans. Reconstructions of primary and model-based CBCT data need to be segmented for proper visualisation and interpretation of perfusion maps. This research proposes Turbolift learning, which trains a modified version of the multi-scale Attention UNet on different liver segmentation tasks serially, following the order of the trainings CT, CBCT, CBCT TST - making the previous trainings act as pre-training stages for the subsequent ones - addressing the problem of limited number of datasets for training. For the final task of liver segmentation from CBCT TST, the proposed method achieved an overall Dice scores of 0.874$\pm$0.031 and 0.905$\pm$0.007 in 6-fold and 4-fold cross-validation experiments, respectively - securing statistically significant improvements over the model, which was trained only for that task. Experiments revealed that Turbolift not only improves the overall performance of the model but also makes it robust against artefacts originating from the embolisation materials and truncation artefacts. Additionally, in-depth analyses confirmed the order of the segmentation tasks. This paper shows the potential of segmenting the liver from CT, CBCT, and CBCT TST, learning from the available limited training data, which can possibly be used in the future for the visualisation and evaluation of the perfusion maps for the treatment evaluation of liver diseases.

106.Structural Causal 3D Reconstruction ⬇️

This paper considers the problem of unsupervised 3D object reconstruction from in-the-wild single-view images. Due to ambiguity and intrinsic ill-posedness, this problem is inherently difficult to solve and therefore requires strong regularization to achieve disentanglement of different latent factors. Unlike existing works that introduce explicit regularizations into objective functions, we look into a different space for implicit regularization -- the structure of latent space. Specifically, we restrict the structure of latent space to capture a topological causal ordering of latent factors (i.e., representing causal dependency as a directed acyclic graph). We first show that different causal orderings matter for 3D reconstruction, and then explore several approaches to find a task-dependent causal factor ordering. Our experiments demonstrate that the latent space structure indeed serves as an implicit regularization and introduces an inductive bias beneficial for reconstruction.

107.AudioScopeV2: Audio-Visual Attention Architectures for Calibrated Open-Domain On-Screen Sound Separation ⬇️

We introduce AudioScopeV2, a state-of-the-art universal audio-visual on-screen sound separation system which is capable of learning to separate sounds and associate them with on-screen objects by looking at in-the-wild videos. We identify several limitations of previous work on audio-visual on-screen sound separation, including the coarse resolution of spatio-temporal attention, poor convergence of the audio separation model, limited variety in training and evaluation data, and failure to account for the trade off between preservation of on-screen sounds and suppression of off-screen sounds. We provide solutions to all of these issues. Our proposed cross-modal and self-attention network architectures capture audio-visual dependencies at a finer resolution over time, and we also propose efficient separable variants that are capable of scaling to longer videos without sacrificing much performance. We also find that pre-training the separation model only on audio greatly improves results. For training and evaluation, we collected new human annotations of onscreen sounds from a large database of in-the-wild videos (YFCC100M). This new dataset is more diverse and challenging. Finally, we propose a calibration procedure that allows exact tuning of on-screen reconstruction versus off-screen suppression, which greatly simplifies comparing performance between models with different operating points. Overall, our experimental results show marked improvements in on-screen separation performance under much more general conditions than previous methods with minimal additional computational complexity.

108.Continual Variational Autoencoder Learning via Online Cooperative Memorization ⬇️

Due to their inference, data representation and reconstruction properties, Variational Autoencoders (VAE) have been successfully used in continual learning classification tasks. However, their ability to generate images with specifications corresponding to the classes and databases learned during Continual Learning (CL) is not well understood and catastrophic forgetting remains a significant challenge. In this paper, we firstly analyze the forgetting behaviour of VAEs by developing a new theoretical framework that formulates CL as a dynamic optimal transport problem. This framework proves approximate bounds to the data likelihood without requiring the task information and explains how the prior knowledge is lost during the training process. We then propose a novel memory buffering approach, namely the Online Cooperative Memorization (OCM) framework, which consists of a Short-Term Memory (STM) that continually stores recent samples to provide future information for the model, and a Long-Term Memory (LTM) aiming to preserve a wide diversity of samples. The proposed OCM transfers certain samples from STM to LTM according to the information diversity selection criterion without requiring any supervised signals. The OCM framework is then combined with a dynamic VAE expansion mixture network for further enhancing its performance.

109.World Robot Challenge 2020 -- Partner Robot: A Data-Driven Approach for Room Tidying with Mobile Manipulator ⬇️

Tidying up a household environment using a mobile manipulator poses various challenges in robotics, such as adaptation to large real-world environmental variations, and safe and robust deployment in the presence of humans.The Partner Robot Challenge in World Robot Challenge (WRC) 2020, a global competition held in September 2021, benchmarked tidying tasks in the real home environments, and importantly, tested for full system performances.For this challenge, we developed an entire household service robot system, which leverages a data-driven approach to adapt to numerous edge cases that occur during the execution, instead of classical manual pre-programmed this http URL this paper, we describe the core ingredients of the proposed robot system, including visual recognition, object manipulation, and motion planning. Our robot system won the second prize, verifying the effectiveness and potential of data-driven robot systems for mobile manipulation in home environments.

110.Model Compression for Resource-Constrained Mobile Robots ⬇️

The number of mobile robots with constrained computing resources that need to execute complex machine learning models has been increasing during the past decade. Commonly, these robots rely on edge infrastructure accessible over wireless communication to execute heavy computational complex tasks. However, the edge might become unavailable and, consequently, oblige the execution of the tasks on the robot. This work focuses on making it possible to execute the tasks on the robots by reducing the complexity and the total number of parameters of pre-trained computer vision models. This is achieved by using model compression techniques such as Pruning and Knowledge Distillation. These compression techniques have strong theoretical and practical foundations, but their combined usage has not been widely explored in the literature. Therefore, this work especially focuses on investigating the effects of combining these two compression techniques. The results of this work reveal that up to 90% of the total number of parameters of a computer vision model can be removed without any considerable reduction in the model's accuracy.