Here, we list some papers related to transfer learning by date (starting from 2021-07). For papers older than 2021-07, please refer to the papers by topic, which contains more papers.
-
Multi-Modal Domain Adaptation Across Video Scenes for Temporal Video Grounding [arxiv]
- Multi-modal domain adaptation 多模态领域自适应
-
Domain Adaptive Graph Classification [arxiv]
- Domain adaptive graph classification 域适应的图分类
-
Understanding and Estimating Domain Complexity Across Domains [arxiv]
- Understanding and estimating domain complexity 解释领域复杂性
-
Prompt-based Domain Discrimination for Multi-source Time Series Domain Adaptation [arxiv]
- Prompt-based domain discrimination for time series domain adaptation 基于prompt的时间序列域自适应
-
NeurIPS'23 SwapPrompt: Test-Time Prompt Adaptation for Vision-Language Models [arxiv]
- Test-time prompt adaptation for vision language models 对视觉-语言大模型的测试时prompt自适应
-
AAAI24 Relax Image-Specific Prompt Requirement in SAM: A Single Generic Prompt for Segmenting Camouflaged Objects [arxiv][code]
- A training-free test-time adaptation approach to relax the instance-specific prompts requirment in SAM.
-
Open Domain Generalization with a Single Network by Regularization Exploiting Pre-trained Features [arxiv]
- Open domain generalization with a single network 用单一网络结构进行开放式domain generalizaition
-
Stronger, Fewer, & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentation [arxiv]
- Using vision foundation models for domain genealized semantic segmentation 用视觉基础模型进行域泛化语义分割
-
DARNet: Bridging Domain Gaps in Cross-Domain Few-Shot Segmentation with Dynamic Adaptation [arxiv]
- Dynamic adaptation for cross-domain few-shot segmentation 动态适配用于跨领域小样本分割
-
A Unified Framework for Unsupervised Domain Adaptation based on Instance Weighting [arxiv]
- Instance weighting for domain adaptation 样本加权用于领域自适应
-
Target-agnostic Source-free Domain Adaptation for Regression Tasks [arxiv]
- Target-agnostic source-free DA for regression 用于回归任务的source-free DA
-
On the Out-Of-Distribution Robustness of Self-Supervised Representation Learning for Phonocardiogram Signals [arxiv]
- OOD robustness for self-supervised learning for phonocardiogram 心音图信号自监督的OOD鲁棒性
-
Student Activity Recognition in Classroom Environments using Transfer Learning [arxiv]
- Using transfer learning to recognize student activities 用迁移学习来识别学生课堂行为
-
A2XP: Towards Private Domain Generalization [arxiv]
- Private domain generalization 隐私保护的domain generalization
-
Layer-wise Auto-Weighting for Non-Stationary Test-Time Adaptation [arxiv]
- Auto-weighting for test-time adaptation 自动权重的TTA
-
Domain Generalization by Learning from Privileged Medical Imaging Information [arxiv]
- Domain generalizaiton by learning from privileged medical imageing inforamtion
-
SSL-DG: Rethinking and Fusing Semi-supervised Learning and Domain Generalization in Medical Image Segmentation [arxiv]
- Semi-supervised learning + domain generalization 把半监督和领域泛化结合在一起
-
WACV'24 Learning Class and Domain Augmentations for Single-Source Open-Domain Generalization [arxiv]
- Class and domain augmentation for single-source open-domain DG 结合类和domain增强做单源DG
-
Proposal-Level Unsupervised Domain Adaptation for Open World Unbiased Detector [arxiv]
- Proposal-level unsupervised domain adaptation
-
Robust Fine-Tuning of Vision-Language Models for Domain Generalization [arxiv]
- Robust fine-tuning for domain generalization 用于领域泛化的鲁棒微调
-
NeurIPS 2023 Distilling Out-of-Distribution Robustness from Vision-Language Foundation Models [arxiv]
- Distill OOD robustness from vision-language foundational models 从VLM模型中蒸馏出OOD鲁棒性
-
UbiComp 2024 Optimization-Free Test-Time Adaptation for Cross-Person Activity Recognition [arxiv]
- Test-time adaptation for activity recognition 测试时adaptation用于行为识别
-
PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization [arxiv]
- Prompt-driven style generation for source-free domain generalization
-
A Survey of Heterogeneous Transfer Learning [arxiv]
- A recent survey of heterogeneous transfer learning 一篇最近的关于异构迁移学习的综述
-
Equivariant Adaptation of Large Pre-Trained Models [arxiv]
- Equivariant adaptation of large pre-trained models 对大模型进行等边自适应
-
Effective and Parameter-Efficient Reusing Fine-Tuned Models [arxiv]
- Effective and parameter-efficient reusing fine-tuned models 高效使用预训练模型
-
Prompting-based Efficient Temporal Domain Generalization [arxiv]
- Prompt based temporal domain generalization 基于prompt的时间域domain generalization
-
Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks [arxiv]
- Noisy model learning: fine-tuning to supress the bad effect of noisy pretraining data 通过使用轻量级finetune减少噪音预训练数据对下游任务的影响
-
ZooPFL: Exploring Black-box Foundation Models for Personalized Federated Learning [arxiv]
- Black-box foundation models for personalized federated learning 黑盒的blackbox模型进行个性化迁移学习
-
Domain Generalization with Fourier Transform and Soft Thresholding [arxiv]
- Domain generalization with Fourier transform 基于傅里叶变换和软阈值进行domain generalization
-
DePT: Decomposed Prompt Tuning for Parameter-Efficient Fine-tuning [arxiv]
- Decomposed prompt tuning for parameter-efficient fine-tuning 基于分解prompt tuning的参数高效微调
-
Better Practices for Domain Adaptation [arxiv]
- Better practice for domain adaptation
-
Domain Adaptation for Efficiently Fine-tuning Vision Transformer with Encrypted Images [arxiv]
- Domain adaptation for efficient ViT
-
Robust Activity Recognition for Adaptive Worker-Robot Interaction using Transfer Learning [arxiv]
- Activity recognition using domain adaptation
-
IJCV'23 Exploring Vision-Language Models for Imbalanced Learning [arxiv] [code]
- Explore vision-language models for imbalanced learning 探索视觉大模型在不平衡问题上的表现
-
ICCV'23 Improving Generalization of Adversarial Training via Robust Critical Fine-Tuning [arxiv] [code]
- 达到对抗鲁棒性和泛化能力的trade off
-
ICCV'23 Domain-Specificity Inducing Transformers for Source-Free Domain Adaptation [arxiv]
- Domain-specificity for source-free DA 用领域特异性驱动的source-free DA
-
Unsupervised Domain Adaptation via Domain-Adaptive Diffusion [arxiv]
- Domain-adaptive diffusion for domain adaptation 领域自适应的diffusion
-
Multi-Scale and Multi-Layer Contrastive Learning for Domain Generalization [arxiv]
- Multi-scale and multi-layer contrastive learning for DG 多尺度和多层对比学习用于DG
-
Exploring the Transfer Learning Capabilities of CLIP in Domain Generalization for Diabetic Retinopathy [arxiv]
- Domain generalization for diabetic retinopathy 用领域泛化进行糖尿病视网膜病
-
Federated Fine-tuning of Billion-Sized Language Models across Mobile Devices [arxiv]
- Federated fine-tuning for large models 大模型联邦微调
-
Source-Free Collaborative Domain Adaptation via Multi-Perspective Feature Enrichment for Functional MRI Analysis [arxiv]
- Source-free domain adaptation for MRI analysis
-
Towards Realistic Unsupervised Fine-tuning with CLIP [arxiv]
- Unsupervised fine-tuning of CLIP
-
Fine-tuning can cripple your foundation model; preserving features may be the solution [arxiv]
- Fine-tuning will cripple foundation model
-
Exploring Transfer Learning in Medical Image Segmentation using Vision-Language Models [arxiv]
- Transfer learning for medical image segmentation
-
Transfer Learning for Portfolio Optimization [arxiv]
- Transfer learning for portfolio optimization
-
NormAUG: Normalization-guided Augmentation for Domain Generalization [arxiv]
- Normalization augmentation for domain generalization
-
Benchmarking Algorithms for Federated Domain Generalization [arxiv]
- Benchmark algorthms for federated domain generalization 对联邦域泛化算法进行的benchmark
-
DISPEL: Domain Generalization via Domain-Specific Liberating [arxiv]
- Domain generalization via domain-specific liberating
-
Review of Large Vision Models and Visual Prompt Engineering [arxiv]
- A survey of large vision model and prompt tuning 一个关于大视觉模型的prompt tuning的综述
-
Intra- & Extra-Source Exemplar-Based Style Synthesis for Improved Domain Generalization [arxiv]
- Exemplar-based style synthesis for domain generalization 样例格式合成用于DG
-
SAM-DA: UAV Tracks Anything at Night with SAM-Powered Domain Adaptation [arxiv]
- Using SAM for domain adaptation 使用segment anything进行domain adaptation
-
Unified Transfer Learning Models for High-Dimensional Linear Regression [arxiv]
- Transfer learning for high-dimensional linar regression 迁移学习用于高维线性回归
-
Pruning for Better Domain Generalizability [arxiv]
- Using pruning for better domain generalization 使用剪枝操作进行domain generalization
-
TMLR'23 Generalizability of Adversarial Robustness Under Distribution Shifts [openreview]
- Evaluate the OOD perormance of adversarial training 评测对抗训练模型的OOD鲁棒性
-
Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning [arxiv]
- A guide for parameter-efficient fine-tuning 一个对parameter efficient fine-tuning的全面介绍
-
ICML'23 A Kernel-Based View of Language Model Fine-Tuning [arxiv]
- A kernel-based view of language model fine-tuning 一种以kernel的视角来看待fine-tuning的方法
-
ICML'23 Improving Visual Prompt Tuning for Self-supervised Vision Transformers [arxiv]
- Improving visual prompt tuning for self-supervision 为自监督模型提高其 prompt tuning 表现
-
Cross-Database and Cross-Channel ECG Arrhythmia Heartbeat Classification Based on Unsupervised Domain Adaptation [arxiv]
- EEG using unsupervised domain adaptation 用无监督DA来进行EEG心跳分类
-
Real-Time Online Unsupervised Domain Adaptation for Real-World Person Re-identification [arxiv]
- Real-time online unsupervised domain adaptation for REID 无监督DA用于REID
-
Federated Domain Generalization: A Survey [arxiv]
- A survey on federated domain generalization 一篇关于联邦域泛化的综述
-
Domain Generalization for Domain-Linked Classes [arxiv]
- Domain generalization for domain-linked classes
-
Can We Evaluate Domain Adaptation Models Without Target-Domain Labels? A Metric for Unsupervised Evaluation of Domain Adaptation [arxiv]
- Evaluate domain adaptation models 评测domain adaptation的模型
-
Universal Test-time Adaptation through Weight Ensembling, Diversity Weighting, and Prior Correction [arxiv]
- Universal test-time adaptation
-
Adapting Pre-trained Language Models to Vision-Language Tasks via Dynamic Visual Prompting [arxiv]
- Using dynamic visual prompting for model adaptation 用动态视觉prompt进行模型适配
-
Selective Mixup Helps with Distribution Shifts, But Not (Only) because of Mixup [arxiv]
- Why mixup works for domain generalization? 系统性研究为啥mixup对OOD很work
-
ACL'23 Parameter-Efficient Fine-Tuning without Introducing New Latency [arxiv]
- Parameter-efficient finetuning 参数高效的finetune
-
Universal Domain Adaptation from Foundation Models [arxiv]
- Using foundation models for universal domain adaptation
-
Ahead-of-Time P-Tuning [arxiv]
- Ahead-ot-time P-tuning for language models
-
Multi-Source to Multi-Target Decentralized Federated Domain Adaptation [arxiv]
- Decentralized federated domain adaptation
-
Benchmarking Low-Shot Robustness to Natural Distribution Shifts [arxiv]
- Low-shot robustness to distribution shifts
-
Multi-Source to Multi-Target Decentralized Federated Domain Adaptation [arxiv]
- Multi-source to multi-target federated domain adaptation 多源多目标的联邦域自适应
-
ICML'23 AdaNPC: Exploring Non-Parametric Classifier for Test-Time Adaptation [arxiv]
- Adaptive test-time adaptation 非参数化分类器进行测试时adaptation
-
Improved Test-Time Adaptation for Domain Generalization [arxiv]
- Improved test-time adaptation for domain generalization
-
Reweighted Mixup for Subpopulation Shift [arxiv]
- Reweighted mixup for subpopulation shift
-
CVPR'23 Zero-shot Generative Model Adaptation via Image-specific Prompt Learning [arxiv]
- Zero-shot generative model adaptation via image-specific prompt learning 零样本的生成模型adaptation
-
Source-free Domain Adaptation Requires Penalized Diversity [arxiv]
- Source-free DA requires penalized diversity
-
Domain Generalization with Adversarial Intensity Attack for Medical Image Segmentation [arxiv]
- Domain generalization for medical segmentation 用domain generalization进行医学分割
-
CVPR'23 Meta-causal Learning for Single Domain Generalization [arxiv]
- Meta-causal learning for domain generalization
-
Domain Generalization In Robust Invariant Representation [arxiv]
- Domain generalization in robust invariant representation
-
Beyond Empirical Risk Minimization: Local Structure Preserving Regularization for Improving Adversarial Robustness [arxiv]
- Local structure preserving for adversarial robustness 通过保留局部结构来进行对抗鲁棒性
-
TFS-ViT: Token-Level Feature Stylization for Domain Generalization [arxiv]
- Token-level feature stylization for domain generalization 用token-level特征变换进行domain generalization
-
Are Data-driven Explanations Robust against Out-of-distribution Data? [arxiv]
- Data-driven explanations robust? 探索数据驱动的解释是否是OOD鲁棒的
-
ERM++: An Improved Baseline for Domain Generalization [arxiv]
- Improved ERM for domain generalization 提高的ERM用于domain generalization
-
CVPR'23 Feature Alignment and Uniformity for Test Time Adaptation [arxiv]
- Feature alignment for test-time adaptation 使用特征对齐进行测试时adaptation
-
Finding Competence Regions in Domain Generalization [arxiv]
- Finding competence regions in domain generalization 在DG中发现能力区域
-
CVPR'23 TWINS: A Fine-Tuning Framework for Improved Transferability of Adversarial Robustness and Generalization [arxiv]
- Improve generalization and adversarial robustness 同时提高鲁棒性和泛化性
-
CVPR'23 Trainable Projected Gradient Method for Robust Fine-tuning [arxiv]
- Trainable PGD for robust fine-tuning 可训练的pgd用于鲁棒的微调技术
-
Parameter-Efficient Tuning Makes a Good Classification Head [arxiv]
- Parameter-efficient tuning makes a good classification head 参数高效的迁移学习成就一个好的分类头
-
Complementary Domain Adaptation and Generalization for Unsupervised Continual Domain Shift Learning [arxiv]
- Continual domain shift learning using adaptation and generalization 使用 adaptation和DG进行持续分布变化的学习
-
CVPR'23 A New Benchmark: On the Utility of Synthetic Data with Blender for Bare Supervised Learning and Downstream Domain Adaptation [arxiv]
- A new benchmark for domain adaptation 一个对于domain adaptation最新的benchmark
-
Unsupervised domain adaptation by learning using privileged information [arxiv]
- Domain adaptation by privileged information 使用高级信息进行domain adaptation
-
A Unified Continual Learning Framework with General Parameter-Efficient Tuning [arxiv]
- A continual learning framework for parameter-efficient tuning 一个对于参数高效迁移的连续学习框架
-
CVPR'23 Sharpness-Aware Gradient Matching for Domain Generalization [arxiv]
- Sharpness-aware gradient matching for DG 利用梯度匹配进行domain generalization
-
TempT: Temporal consistency for Test-time adaptation [arxiv]
- Temporeal consistency for test-time adaptation 时间一致性用于test-time adaptation
-
TMLR'23 Learn, Unlearn and Relearn: An Online Learning Paradigm for Deep Neural Networks [arxiv]
- A framework for online learning 一个在线学习的框架
-
ICLR'23 workshop SPDF: Sparse Pre-training and Dense Fine-tuning for Large Language Models [arxiv]
- Sparse pre-training and dense fine-tuning
-
CVPR'23 ALOFT: A Lightweight MLP-like Architecture with Dynamic Low-frequency Transform for Domain Generalization [arxiv]
- A lightweight module for domain generalization 一个用于DG的轻量级模块
-
ICLR'23 Contrastive Alignment of Vision to Language Through Parameter-Efficient Transfer Learning [arxiv]
- Contrastive alignment for vision language models using transfer learning 使用参数高效迁移进行视觉语言模型的对比对齐
-
Probabilistic Domain Adaptation for Biomedical Image Segmentation [arxiv]
- Probabilistic domain adaptation for biomedical image segmentation 概率的domain adaptation用于生物医疗图像分割
-
Imbalanced Domain Generalization for Robust Single Cell Classification in Hematological Cytomorphology [arxiv]
- Imbalanced domain generalization for single cell classification 不平衡的DG用于单细胞分类
-
Revisit Parameter-Efficient Transfer Learning: A Two-Stage Paradigm [arxiv]
- Parameter-efficient transfer learning: a two-stage approach 一种两阶段的参数高效迁移学习
-
Unsupervised Cumulative Domain Adaptation for Foggy Scene Optical Flow [arxiv]
- Domain adaptation for foggy scene optical flow 领域自适应用于雾场景的光流
-
ICLR'23 AutoTransfer: AutoML with Knowledge Transfer -- An Application to Graph Neural Networks [arxiv]
- GNN with autoML transfer learning 用于GNN的自动迁移学习
-
Transfer Learning for Real-time Deployment of a Screening Tool for Depression Detection Using Actigraphy [arxiv]
- Transfer learning for Depression detection 迁移学习用于脉动计焦虑检测
-
Domain Generalization via Nuclear Norm Regularization [arxiv]
- Domain generalization via nuclear norm regularization 使用核归一化进行domain generalization
-
To Stay or Not to Stay in the Pre-train Basin: Insights on Ensembling in Transfer Learning [arxiv]
- Ensembling in transfer learning 调研迁移学习中的集成
-
CVPR'13 Masked Images Are Counterfactual Samples for Robust Fine-tuning [arxiv]
- Masked images for robust fine-tuning 调研masked image对于fine-tuning的影响
-
FedCLIP: Fast Generalization and Personalization for CLIP in Federated Learning [arxiv]
- Fast generalization for federated CLIP 在联邦中进行快速的CLIP训练
-
Robust Representation Learning with Self-Distillation for Domain Generalization [arxiv]
- Robust representation learning with self-distillation
-
ICLR-23 Temporal Coherent Test-Time Optimization for Robust Video Classification [arxiv]
- Temporal distribution shift in video classification
-
WSDM-23 A tutorial on domain generalization [link] | [website]
- A tutorial on domain generalization
-
On the Robustness of ChatGPT: An Adversarial and Out-of-distribution Perspective [arxiv] | [code]
- Adversarial and OOD evaluation of ChatGPT 对ChatGPT鲁棒性的评测
-
Transfer learning for process design with reinforcement learning [arxiv]
- Transfer learning for process design with reinforcement learning 使用强化迁移学习进行过程设计
-
Domain Adaptation for Time Series Under Feature and Label Shifts [arxiv]
- Domain adaptation for time series 用于时间序列的domain adaptation
-
How Reliable is Your Regression Model's Uncertainty Under Real-World Distribution Shifts? [arxiv]
- Regression models uncertainty for distribution shift 回归模型对于分布漂移的不确定性
-
ICLR'23 SoftMatch: Addressing the Quantity-Quality Tradeoff in Semi-supervised Learning [arxiv]
- Semi-supervised learning algorithm 解决标签质量问题的半监督学习方法
-
Empirical Study on Optimizer Selection for Out-of-Distribution Generalization [arxiv]
- Opimizer selection for OOD generalization OOD泛化中的学习器选择
-
ICML'22 Understanding the failure modes of out-of-distribution generalization [arxiv]
- Understand the failure modes of OOD generalization 探索OOD泛化中的失败现象
-
ICLR'23 Out-of-distribution Representation Learning for Time Series Classification [arxiv]
- OOD for time series classification 时间序列分类的OOD算法
-
ICLR'23 FreeMatch: Self-adaptive Thresholding for Semi-supervised Learning [arxiv]
- New baseline for semi-supervised learning 半监督学习新算法
-
CLIP the Gap: A Single Domain Generalization Approach for Object Detection [arxiv]
- Using CLIP for domain generalization object detection 使用CLIP进行域泛化的目标检测
-
Language-Informed Transfer Learning for Embodied Household Activities [arxiv]
- Transfer learning for robust control in household 在家居机器人上使用强化迁移学习
-
Does progress on ImageNet transfer to real-world datasets? [arxiv]
- ImageNet accuracy does not transfer to down-stream tasks
-
TPAMI'23 Source-Free Unsupervised Domain Adaptation: A Survey [arxiv]
- A survey on source-free domain adaptation 关于source-free DA的一个最新综述
-
Discriminative Radial Domain Adaptation [arxiv]
- Discriminative radial domain adaptation 判别性的放射式domain adaptation
-
WACV'23 Cross-Domain Video Anomaly Detection without Target Domain Adaptation [arxiv]
- Cross-domain video anomaly detection without target domain adaptation 跨域视频异常检测
-
Co-Learning with Pre-Trained Networks Improves Source-Free Domain Adaptation [arxiv]
- Pre-trained models for source-free domain adaptation 用预训练模型进行source-free DA
-
TMLR'22 A Unified Survey on Anomaly, Novelty, Open-Set, and Out of-Distribution Detection: Solutions and Future Challenges [openreview]
- A recent survey on OOD/anomaly detection 一篇最新的关于OOD/anomaly detection的综述
-
NeurIPS'18 A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks [paper]
- Using class-conditional distribution for OOD detection 使用类条件概率进行OOD检测
-
ICLR'22 Discrete Representations Strengthen Vision Transformer Robustness [arxiv]
- Embed discrete representation for OOD generalization 在ViT中加入离散表征增强OOD性能
-
CONDA: Continual Unsupervised Domain Adaptation Learning in Visual Perception for Self-Driving Cars [arxiv]
- Continual DA for self-driving cars 连续的domain adaptation用于自动驾驶
-
Finetune like you pretrain: Improved finetuning of zero-shot vision models [arxiv]]
- Improved fine-tuning of zero-shot models 针对zero-shot model提高fine-tuneing
-
ECCV-22 DecoupleNet: Decoupled Network for Domain Adaptive Semantic Segmentation [arXiv] [Code]
- Domain adaptation in semantic segmentation 语义分割域适应
-
Robust Mean Teacher for Continual and Gradual Test-Time Adaptation [arxiv]
- Mean teacher for test-time adaptation 在测试时用mean teacher进行适配
-
Learning to Learn Domain-invariant Parameters for Domain Generalization [[arxiv](Learning to Learn Domain-invariant Parameters for Domain Generalization)]
- Learning to learn domain-invariant parameters for DG 元学习进行domain generalization
-
HMOE: Hypernetwork-based Mixture of Experts for Domain Generalization [arxiv]
- Hypernetwork-based ensembling for domain generalization 超网络构成的集成学习用于domain generalization
-
The Evolution of Out-of-Distribution Robustness Throughout Fine-Tuning [arxiv]
- OOD using fine-tuning 系统总结了基于fine-tuning进行OOD的一些结果
-
GLUE-X: Evaluating Natural Language Understanding Models from an Out-of-distribution Generalization Perspective [arxiv]
- OOD for natural language processing evaluation 提出GLUE-X用于OOD在NLP数据上的评估
-
CVPR'22 Delving Deep Into the Generalization of Vision Transformers Under Distribution Shifts [arxiv]
- Vision transformers generalization under distribution shifts 评估ViT的分布漂移
-
NeurIPS'22 Models Out of Line: A Fourier Lens on Distribution Shift Robustness [arxiv]
- A fourier lens on distribution shift robustness 通过傅里叶视角来看分布漂移的鲁棒性
-
CVPR'22 Does Robustness on ImageNet Transfer to Downstream Tasks? [arxiv]
- Does robustness on imagenet transfer lto downstream tasks?
-
Normalization Perturbation: A Simple Domain Generalization Method for Real-World Domain Shifts [arxiv]
- Normalization perturbation for domain generalization 通过归一化扰动来进行domain generalization
-
FIXED: Frustraitingly easy domain generalization using Mixup [arxiv]
- 使用Mixup进行domain generalization
-
Learning to Learn Domain-invariant Parameters for Domain Generalization [arxiv]
- Learning to learn domain-invariant parameters for domain generalization
-
NeurIPS'22 Improved Fine-Tuning by Better Leveraging Pre-Training Data [openreview]
- Using pre-training data for fine-tuning 用预训练数据来做微调
-
NeurIPS'22 Divide and Contrast: Source-free Domain Adaptation via Adaptive Contrastive Learning [openreview]
- Adaptive contrastive learning for source-free DA 自适应的对比学习用于source-free DA
-
NeurIPS'22 LOG: Active Model Adaptation for Label-Efficient OOD Generalization [openreview]
- Model adaptation for label-efficient OOD generalization
-
NeurIPS'22 MetaTeacher: Coordinating Multi-Model Domain Adaptation for Medical Image Classification [openreview]
- Multi-model domain adaptation mor medical image classification 多模型DA用于医疗数据
-
NeurIPS'22 Domain Adaptation under Open Set Label Shift [openreview]
- Domain adaptation under open set label shift 在开放集的label shift中的DA
-
NeurIPS'22 Domain Generalization without Excess Empirical Risk [openreview]
- Domain generalization without excess empirical risk
-
NeurIPS'22 FedSR: A Simple and Effective Domain Generalization Method for Federated Learning [openreview]
- FedSR for federated learning domain generalization 用于联邦学习的domain generalization
-
NeurIPS'22 Probable Domain Generalization via Quantile Risk Minimization [openreview]
- Domain generalization with quantile risk minimization 用quantile风险最小化的domain generalization
-
NeurIPS'22 Beyond Not-Forgetting: Continual Learning with Backward Knowledge Transfer [arxiv]
- Continual learning with backward knowledge transfer 反向知识迁移的持续学习
-
NeurIPS'22 Test Time Adaptation via Conjugate Pseudo-labels [openreview]
- Test-time adaptation with conjugate pseudo-labels 用伪标签进行测试时adaptation
-
NeurIPS'22 Your Out-of-Distribution Detection Method is Not Robust! [openreview]
- OOD models are not robust 分布外泛化模型不够鲁棒
-
NeurIPS'22 Respecting Transfer Gap in Knowledge Distillation [arxiv]
- Transfer gap in distillation 知识蒸馏中的迁移gap
-
Transfer of Machine Learning Fairness across Domains [arxiv]
- Fairness transfer in transfer learning 迁移学习中的公平性迁移
-
On Fine-Tuned Deep Features for Unsupervised Domain Adaptation [arxiv]
- Fine-tuned features for domain adaptation 微调的特征用于域自适应
-
WACV-23 ConfMix: Unsupervised Domain Adaptation for Object Detection via Confidence-based Mixing [arxiv]
- Domain adaptation for object detection using confidence mixing 用置信度mix做domain adaptation
-
CVPR-20 Regularizing CNN Transfer Learning With Randomised Regression [arxiv]
- Using randomized regression to regularize CNN 用随机回归约束CNN迁移学习
-
AAAI-21 TransTailor: Pruning the Pre-trained Model for Improved Transfer Learning [arxiv]
- Pruning pre-trained model for transfer learning 通过对预训练模型进行剪枝来进行迁移学习
-
PhDthesis Generalizing in the Real World with Representation Learning [arxiv]
- A phd thesis about generalization in real world 一篇关于现实世界如何做Generalization的博士论文
-
The Evolution of Out-of-Distribution Robustness Throughout Fine-Tuning [arxiv]
- Evolution of OOD robustness by fine-tuning
-
Visual Prompt Tuning for Test-time Domain Adaptation [arxiv]
- VPT for test-time adaptation 用prompt tuning进行test-time DA
-
Unsupervised Domain Adaptation for COVID-19 Information Service with Contrastive Adversarial Domain Mixup [arxiv]
- Domain adaptation for COVID-19 用DA进行COVID-19预测
-
ICONIP'22 IDPL: Intra-subdomain adaptation adversarial learning segmentation method based on Dynamic Pseudo Labels [arxiv]
- Intra-domain adaptation for segmentation 子领域对抗Adaptation
-
NeurIPS'22 Polyhistor: Parameter-Efficient Multi-Task Adaptation for Dense Vision Tasks [arxiv]
- Parameter-efficient multi-task adaptation 参数高效的多任务adaptation
-
Out-of-Distribution Generalization in Algorithmic Reasoning Through Curriculum Learning [arxiv]
- OOD in algorithmic reasoning 算法reasoning过程中的OOD
-
Towards Out-of-Distribution Adversarial Robustness [arxiv]
- OOD adversarial robustness OOD对抗鲁棒性
-
TripleE: Easy Domain Generalization via Episodic Replay [arxiv]
- Easy domain generalization by episodic replay
-
Deep Spatial Domain Generalization [arxiv]
- Deep spatial domain generalization
-
Assaying Out-Of-Distribution Generalization in Transfer Learning [arXiv]
- A lot of experiments to show OOD performance
-
ICML-21 Accuracy on the Line: on the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization [arxiv]
- Strong correlation between ID and OOD
-
Deep Domain Adaptation for Detecting Bomb Craters in Aerial Images [arxiv]
- Bomb craters detection using domain adaptation 用DA检测遥感图像中的炮弹弹坑
-
WACV-23 TeST: Test-time Self-Training under Distribution Shift [arxiv]
- Test-time self-training 测试时训练
-
StyleTime: Style Transfer for Synthetic Time Series Generation [arxiv]
- Style transfer for time series generation 时间序列生成的风格迁移
-
Robust Domain Adaptation for Machine Reading Comprehension [arxiv]
- Domain adaptation for machine reading comprehension 机器阅读理解的domain adaptation
-
Generalized representations learning for time series classification [arxiv]
- OOD for time series classification 域泛化用于时间序列分类
-
USB: A Unified Semi-supervised Learning Benchmark [arxiv] [code]
- Unified semi-supervised learning codebase 半监督学习统一代码库
-
Test-Time Training with Masked Autoencoders [arxiv]
- Test-time training with MAE MAE的测试时训练
-
Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models [arxiv]
- Test-time prompt tuning 测试时的prompt tuning
-
TeST: test-time self-training under distribution shift [arxiv]
- Test-time self-training 测试时的self-training
-
Language-aware Domain Generalization Network for Cross-Scene Hyperspectral Image Classification [arxiv]
- Domain generalization for cross-scene hyperspectral image classification 域泛化用于高光谱图像分类
-
IEEE-TMM'22 Uncertainty Modeling for Robust Domain Adaptation Under Noisy Environments [IEEE]
- Uncertainty modeling for domain adaptation 噪声环境下的domain adaptation
-
Improving Robustness to Out-of-Distribution Data by Frequency-based Augmentation arxiv
- OOD by frequency-based augmentation 通过基于频率的数据增强进行OOD
-
Domain Generalization for Prostate Segmentation in Transrectal Ultrasound Images: A Multi-center Study arxiv
- Domain generalizationfor prostate segmentation 领域泛化用于前列腺分割
-
Domain Adaptation from Scratch arxiv
- Domain adaptation from scratch
-
Towards Optimization and Model Selection for Domain Generalization: A Mixup-guided Solution arxiv
- Model selection for domain generalization 域泛化中的模型选择问题
-
Conv-Adapter: Exploring Parameter Efficient Transfer Learning for ConvNets
- Parameter efficient CNN adapter for transfer learning 参数高效的CNN adapter用于迁移学习
-
Equivariant Disentangled Transformation for Domain Generalization under Combination Shift
- Equivariant disentangled transformation for domain generalization 新的建模domain generalization的思路
-
ECCV-22 workshop Domain-Specific Risk Minimization
- Domain-specific risk minization for OOD 领域特异性风险最小化用于域泛化
-
TPAMI Semi-Supervised and Unsupervised Deep Visual Learning: A Survey
- Survey on semi and unsupervsed learning 半监督和无监督综述
-
Improving video retrieval using multilingual knowledge transfer
- Video retrieval using multilingual knowledge transfer 多语言知识迁移用于视频检索
-
- Battery health estimation using transfer learning 用迁移学习进行电池健康估计
-
IJCAI-22 Domain Generalization through the Lens of Angular Invariance
- Using angular invariance for domain generalization 使用角度不变性进行domain generalization
-
MM-22 Making the Best of Both Worlds: A Domain-Oriented Transformer for Unsupervised Domain Adaptation
- Transformer for domain adaptation 用transformer进行DA
-
Adaptive Domain Generalization via Online Disagreement Minimization
- Online domain generalization via disagreement minimization 在线DG
-
Self-Distilled Vision Transformer for Domain Generalization
- Vision transformer for domain generalization 用ViT做domain generalization
-
NeurIPS-21 The balancing principle for parameter choice in distance-regularized domain adaptation
- Hyperparameter selection for domain adaptation 对adaptation中的正则项系数进行选择
-
Transfer Learning for Segmentation Problems: Choose the Right Encoder and Skip the Decoder
- Transfer learning for segmentation problems 统一表示迁移学习于分割问题的思路
-
TMLR-22 Domain-invariant Feature Exploration for Domain Generalization
- Exploring domain-invariant feature for domain generalization 探索领域不变特征在领域泛化中的应用
-
TIST-22 Domain Generalization for Activity Recognition via Adaptive Feature Fusion
- Domain generalization for activity recognition 领域泛化用于行为识别
-
ECCV-22 Prototype-Guided Continual Adaptation for Class-Incremental Unsupervised Domain Adaptation
- Prototype continual domain adaptation 基于原型的类增量domain adaptation
-
Federated Semi-Supervised Domain Adaptation via Knowledge Transfer
- Federated semi-supervised DA 联邦半监督DA
-
Hyper-Representations for Pre-Training and Transfer Learning
- Hyper-representation for pre-training and fine-tuning 对于预训练和微调的超表示
-
MM-22 Source-Free Domain Adaptation for Real-world Image Dehazing
- Source-free DA for image dehazing 无需源域的迁移用于图像去雾
-
Improved OOD Generalization via Conditional Invariant Regularizer
- Improved OOD generalization via conditional invariant regularizer 通过条件不变正则进行OOD泛化
-
CVPR-22 Segmenting Across Places: The Need for Fair Transfer Learning With Satellite Imagery
- Fair transfer learning with satellite imagery 公平迁移学习
-
Transferability-Guided Cross-Domain Cross-Task Transfer Learning
- Cross-domain cross-task transfer learning 用迁移性指标指导跨领域跨任务迁移
-
Cross-Architecture Knowledge Distillation
- Cross-architecture knowledge distillation 跨架构的知识蒸馏
-
ECCV-22 Knowledge Condensation Distillation
- Knowledge condensation distillation 知识压缩蒸馏
-
An Information-Theoretic Analysis for Transfer Learning: Error Bounds and Applications
- Information-theoretic analysis for transfer learning 用信息理论解释迁移学习
-
A Data-Based Perspective on Transfer Learning
- Analyze the data numbers in transfer learning 分析迁移学习中数据的重要性
-
PAC-Bayesian Domain Adaptation Bounds for Multiclass Learners
- PAC-Bayesian domain adaptation 基于PAC-Bayesian的domain adaptation
-
NeurIPS-21 Parameterized Knowledge Transfer for Personalized Federated Learning
- personalized group knowledge transfer training
- 个性化群体知识迁移
-
ICML-21 Federated Continual Learning with Weighted Inter-client Transfer
- Federated Weighted Inter-client Transfer (FedWeIT) for Federated Continual Learning
- 联邦加权客户端间传输方法，用于联邦持续学习
-
SIGIR-21 FedCT: Federated Collaborative Transfer for Recommendation
- Federated learning for cross-domain recommendation
- 使用联邦迁移学习执行跨域推荐任务
-
KDD-21 Federated Adversarial Debiasing for Fair and Transferable Representations
- Federated Adversarial DEbiasing (FADE)
- 通过对抗性学习对联邦学习过程去除偏见
-
NeurIPS-20 Group Knowledge Transfer: Federated Learning of Large CNNs at the Edge
- Group knowledge transfer training
- 群体知识迁移
-
FL-IJCAI-22 MetaFed: Federated Learning among Federations with Cyclic Knowledge Distillation for Personalized Healthcare
- MetaFed: a new form of federated learning 联邦之联邦学习、新范式
-
Interspeech-22 Decoupled Federated Learning for ASR with Non-IID Data
- Decoupled federated learning for non IID 解耦的联邦架构用于Non-IID语音识别
-
Few-Max: Few-Shot Domain Adaptation for Unsupervised Contrastive Representation Learning
- Few-shot DA for unsupervised constrastive learning 小样本DA用于无监督对比学习
-
The Importance of Background Information for Out of Distribution Generalization
- Background information for OOD generalization 背景信息对于OOD泛化的重要性
-
Zero-Shot AutoML with Pretrained Models
- 用预训练模型进行零样本的自动机器学习
-
How robust are pre-trained models to distribution shift?
- How robust are pre-trained models to distribution shift 评估预训练模型对于distribution shift的鲁棒性
-
- Few-shot transfer learning for image classification 小样本迁移学习用于图像分类
-
COVID-19 Detection using Transfer Learning with Convolutional Neural Network
- COVID-19 using transfer learning 用迁移学习进行COVID-19检测
-
Wav2vec-S: Semi-Supervised Pre-Training for Speech Recognition
- Pretraining for speech recognition 用预训练模型进行语音识别
-
Causal Balancing for Domain Generalization
- Causal balancing for domain generalization 因果平衡用于领域泛化
-
NAACL-22 Modularized Transfer Learning with Multiple Knowledge Graphs for Zero-shot Commonsense Reasoning
- Transfer learning for zero-shot reasoning 迁移学习用于零次常识推理
-
ConFUDA: Contrastive Fewshot Unsupervised Domain Adaptation for Medical Image Segmentation
- Fewshot UDA for medical image segmentation 小样本域自适应用于医疗图像分割
-
One Ring to Bring Them All: Towards Open-Set Recognition under Domain Shift
- Open set recognition with domain shift 开放集+domain shift
-
Toward Certified Robustness Against Real-World Distribution Shifts
- Certified robustness against real-world distribution shifts 真实世界中的distribution shift
-
On Transfer Learning in Functional Linear Regression
- Transfer learning in functional linear regression 迁移学习用于函数式线性回归
-
IJCAI-22 Parameter-Efficient Sparsity for Large Language Models Fine-Tuning
- Parameter-efficient sparsity for language model fine-tuning 参数高效的稀疏学习用于语言模型微调
-
A Domain-adaptive Pre-training Approach for Language Bias Detection in News
- Domain-adaptive pre-training for language bias detection 领域适配预训练用于新闻语言偏见检测
-
ScholarBERT: Bigger is Not Always Better
- Empirical study on fine-tuning experiments 提出ScholarBERT进行大规模finetuning实验
-
ICPR-22 OTAdapt: Optimal Transport-based Approach For Unsupervised Domain Adaptation
- Optimal transport-based domain adaptation 利用最优传输进行领域自适应
-
Temporal Domain Generalization with Drift-Aware Dynamic Neural Network
- Temporal domain generalization with drift-aware dynamic neural network 时序域泛化
-
Active Source Free Domain Adaptation
- Active source-free DA 主动学习-无源域DA
-
Test-Time Robust Personalization for Federated Learning
- Test-time robust personalization for FL 测试时鲁棒联邦学习
-
FreeMatch: Self-adaptive Thresholding for Semi-supervised Learning
- Self-adaptive thresholding for semi-supervised learning 新的自适应阈值半监督方法
-
IJCAI-22 Test-time Fourier Style Calibration for Domain Generalization
- Test-time calibration for domain generalization 用傅立叶变化进行域泛化的测试时矫正
-
Multiple Domain Causal Networks
- Mlutiple domain causal networks 多领域的因果网络
-
ICLR-22 Enhancing Cross-lingual Transfer by Manifold Mixup
- Cross-lingual transfer using manifold mixup 用Mixup进行cross-lingual transfer
-
CVPR-22 workshop Online Unsupervised Domain Adaptation for Person Re-identification
- Online domain adaptation for REID 在线adaptation
-
- Time series domain adaptation 时间序列domain adaptation
-
TIP-22 Spot-adaptive Knowledge Distillation
- Spot-adaptive knowledge distillation 层次自适应的知识蒸馏
-
NAACL-22 Efficient Few-Shot Fine-Tuning for Opinion Summarization
- Few-shot fine-tuning for opinion summarization 小样本微调技术用于评论总结
-
ICME-22 Unsupervised Domain Adaptation Learning for Hierarchical Infant Pose Recognition with Synthetic Data
- Unsupervised domain adaptation for infant pose recognition 用领域自适应进行婴儿姿势识别
Updated at 2022-04-29:
-
ACL-22 Probing Simile Knowledge from Pre-trained Language Models
- Probe simile knowledge from pre-trained model 从预训练模型中找出明喻知识
-
Parkinson's disease diagnostics using AI and natural language knowledge transfer
- Transfer learning for Parkinson's disease diagnostics 迁移学习用于帕金森诊断
-
CVPR-22 MM-TTA: Multi-Modal Test-Time Adaptation for 3D Semantic Segmentation
- Multi-modal test-time adaptation for 3D semantic segmentation 多模态测试时adaptation用于3D语义分割
-
Transfer Learning with Pre-trained Conditional Generative Models
- Transfer learning with pre-trained conditional generative models 条件生成模型用于迁移学习
-
ICLR-22 Towards a Unified View of Parameter-Efficient Transfer Learning
- Unified view of parameter-efficient transfer learning 一个统一视角看待参数高效的迁移学习
-
ICLR-22 Exploring the Limits of Large Scale Pre-training
- Many experiments to explore pre-training 许多实验来探索预训练
-
IEEE TNNLS-22 Towards Personalized Federated Learning
- A survey on personalized federated learning 一个关于个性化联邦学习的综述
-
On Effectively Learning of Knowledge in Continual Pre-training
- Continual per-training 持续的预训练
-
Just Fine-tune Twice: Selective Differential Privacy for Large Language Models
- Differential privacy by just fine-tune twice 通过微调两次进行差分隐私
-
CVPR-22 Safe Self-Refinement for Transformer-based Domain Adaptation
- Transformer-based domain adaptation 基于transformer的domain adaptation
-
Undoing the Damage of Label Shift for Cross-domain Semantic Segmentation
- Handle the label shift in cross-domain semantic segmentation 在跨域语义分割时考虑label shift
-
CVPR-22 workshop Out-Of-Distribution Detection In Unsupervised Continual Learning
- OOD detection in unsupervised continual learning 无监督持续学习中进行OOD检测
-
Transfer Learning for Autonomous Chatter Detection in Machining
- Transfer learning for autonomous chatter detection
-
NAACL-22 GRAM: Fast Fine-tuning of Pre-trained Language Models for Content-based Collaborative Filtering
- Fast fine-tuning for content-based collaborative filtering
- 快速的适用于协同过滤的微调
-
- Finetuning in few-shot learning
- 小样本学习中的微调
-
CVPR-22 Does Robustness on ImageNet Transfer to Downstream Tasks?
- Transfer learning robustness
- 迁移学习鲁棒性
-
Blockchain as an Enabler for Transfer Learning in Smart Environments
- Blockchain transfer learning
- 用区块链进行迁移学习
-
ICLR-22 Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution
- Fin-tuning and linear probing for ood generalization
- 先linear probing最后一层再finetune对OOD任务最好
-
ICLR-22 Asymmetry Learning for Counterfactually-invariant Classification in OOD Tasks
- Asymmetry learning for OOD tasks
- 非对称学习用于OOD任务
-
Gated Domain-Invariant Feature Disentanglement for Domain Generalizable Object Detection
- Channel masking for domain generalization object detection
- 通过一个gate控制channel masking进行object detection DG
-
A Broad Study of Pre-training for Domain Generalization and Adaptation
- A broad study of pre-training models for DA and DG
- 大量的实验进行DA和DG
-
ISPASS-22 Benchmarking Test-Time Unsupervised Deep Neural Network Adaptation on Edge Devices
- Benchmarking test-time adaptation for edge devices
- 在端设备上评测test-time adaptation算法
-
Multi-Source Domain Adaptation Based on Federated Knowledge Alignment
- Multi-source domain adaptation
- 多源域自适应
-
Improving Generalization in Federated Learning by Seeking Flat Minima
- Seeking flat minima for domain generalization in federated learning
- 通过寻找平坦值进行联邦学习领域泛化
-
CVPR-22 Decoupled Knowledge Distillation
- Decoupled knowledge distillation
- 解耦的知识蒸馏
-
SemiPFL: Personalized Semi-Supervised Federated Learning Framework for Edge Intelligence
- Personalized federated learning
- 个性化联邦学习
-
ICSE-22 ReMoS: Reducing Defect Inheritance in Transfer Learning via Relevant Model Slicing | Code | Blog | Video
- Safe transfer learning by reducing defect inheritance
- 安全迁移学习的最新工作
-
ACL-22 Language-Agnostic Meta-Learning for Low-Resource Text-to-Speech with Articulatory Features
- Language-agnostic meta-learning for TTS
- 语言无关的元学习用于TTS
-
Input-Tuning: Adapting Unfamiliar Inputs to Frozen Pretrained Models
- Adapt unfamiliar inputs to frozen pretrained models
- 让固定的预训练模型适配不熟悉的输入
-
One Model, Multiple Tasks: Pathways for Natural Language Understanding
- Pathways for natural language understanding
- 使用一个model用于所有NLP任务
-
Pre-trained Token-replaced Detection Model as Few-shot Learner
- Pre-trained token-replaced detection model as few-shot learner
- 预训练的替换token的检测模型
-
Open Set Domain Adaptation By Novel Class Discovery
- Open set DA by novel class discovery
- 基于新类发现的open set da
-
ICML-21 workshop Domain Adaptation with Factorizable Joint Shift
- Domain adaptation with factorizable joint shift
- 基于可分解的联合漂移的领域自适应
-
ICC-22 Knowledge Transfer in Deep Reinforcement Learning for Slice-Aware Mobility Robustness Optimization
- Knowledge transfer in RL
- 强化迁移学习
-
- Investigate selective prediction approaches in IID, OOD, and ADV settings
- 在独立同分布、分布外、对抗情境中调研选择性预测方法
-
PAKDD-22 Layer Adaptive Deep Neural Networks for Out-of-distribution Detection
- Layer adaptive network for OOD detection
- 层自适应的网络进行OOD检测
-
Learning Semantic Segmentation from Multiple Datasets with Label Shifts
- Learning semantic segmentation from many datasets with label shifts
- 在有标签漂移的情况下从多个数据集中学习语义分割
-
Causal Domain Adaptation with Copula Entropy based Conditional Independence Test
- Use copula entropy based conditional independence test for csusal domain adaptation
- 使用基于copula entopy的条件独立测试进行causal domain adaptation
-
Interpretable Concept-based Prototypical Networks for Few-Shot Learning
- Concept-based prototypical network for few-shot learning
- 基于概念的原型网络用于小样本学习
-
How Well Do Self-Supervised Methods Perform in Cross-Domain Few-Shot Learning?
- Self-supervised learning for cross-domain few-shot
- 自监督用于跨领域小样本
-
Deep Transfer Learning on Satellite Imagery Improves Air Quality Estimates in Developing Nations
- Deep transfer learning for air quality estimate
- 深度迁移学习用于卫星图到空气质量预测
-
ICLR-22 oral A Fine-Grained Analysis on Distribution Shift
- Extensive experiments on distribution shift for OOD
- 大量的实验进行OOD验证
-
ICLR-22 oral Fine-Tuning Distorts Pretrained Features and Underperforms Out-of-Distribution
- Fine-tuning with linear probing for OOD
- 微调加上linear probing用于OOD
-
ICLR-22 spotlight Towards a Unified View of Parameter-Efficient Transfer Learning
- Detailed analysis of parameter-efficient transfer learning
- 对参数高效的迁移学习进行分析
-
ICLR-22 Graph-Relational Domain Adaptation
- Graph-relational domain adapttion using topological structures
- 图级别的domain adaptation，使用拓扑结构
-
- Transfer learning for traffic forecasting across cities
- 用迁移学习进行跨城市的交通流量预测
-
ICLR-22 Uncertainty Modeling for Out-of-Distribution Generalization
- Uncertainty modeling for OOD generalization
- 用于分布外泛化的不确定性建模
-
ICLR-22 BEiT: BERT Pre-Training of Image Transformers
- BERT pre-training of image transformers
- 用BERT的方式pre-train transformer
-
Improved Fine-tuning by Leveraging Pre-training Data: Theory and Practice
- Using pre-training data to improve fine-tuning
- 使用预训练数据来帮助finetune
-
IGLUE: A Benchmark for Transfer Learning across Modalities, Tasks, and Languages
- A benchmark for transfer learning in NLP
- 一个用于NLP跨模态、任务、语言的benchmark
-
- Domain generalization in mass detection in mammography
- Domain generalization进行胸部射线检测
-
Domain-Invariant Representation Learning from EEG with Private Encoders
- Domain-invariant learning from EEG
- 用于EEG信号的领域不变特征研究
-
Gap Minimization for Knowledge Sharing and Transfer
- Multitask learning with gap minimization
- 用于多任务学习的gap minimization方法
-
DROPO: Sim-to-Real Transfer with Offline Domain Randomization
- Sim-to-real transfer with domain randomization
- 用domain randomization进行sim-to-real transfer
-
AAAI-22 Knowledge Sharing via Domain Adaptation in Customs Fraud Detection
- Domain adaptation for fraud detection
- 用领域自适应进行欺诈检测
-
Continual Coarse-to-Fine Domain Adaptation in Semantic Segmentation
- Domain adaptation in semantic segmentation
- 领域自适应在语义分割的应用
-
- An overview of transfer learning for time series data
- 一个用迁移学习进行时间序列分析的小综述
-
A Likelihood Ratio based Domain Adaptation Method for E2E Models
- Domain adaptation for speech recognition
- 用domain adaptation进行语音识别
-
Transfer Learning for Scene Text Recognition in Indian Languages
- Transfer learning for scene text recognition in Indian languages
- 用迁移学习进行印度语的场景文字识别
-
IEEE TMM-22 Decompose to Adapt: Cross-domain Object Detection via Feature Disentanglement
- Invariant and shared components for Faster RCNN detection
- 解耦公共和私有表征进行目标检测
-
Mixture of basis for interpretable continual learning with distribution shifts
- Incremental learning with mixture of basis
- 用mixture of domains进行增量学习
-
TKDE-22 Adaptive Memory Networks with Self-supervised Learning for Unsupervised Anomaly Detection
- Adaptiev memory network for anomaly detection
- 自适应的记忆网络用于异常检测
-
ICIP-22 Meta-Learned Feature Critics for Domain Generalized Semantic Segmentation
- Meta-learning for domain generalization
- 元学习用于domain generalization
-
ICIP-22 Few-Shot Classification in Unseen Domains by Episodic Meta-Learning Across Visual Domains
- Few-shot generalization using meta-learning
- 用元学习进行小样本的泛化
-
Data-Free Knowledge Transfer: A Survey
- A survey on data-free distillation and source-free DA
- 一篇关于data-free蒸馏和source-free DA的综述
-
An Ensemble of Pre-trained Transformer Models For Imbalanced Multiclass Malware Classification
- An ensemble of pre-trained transformer for malware classification
- 预训练的transformer通过集成进行恶意软件检测
-
Optimal Representations for Covariate Shift
- Learning optimal representations for covariate shift
- 为covariate shift学习最优的表达
-
Transfer-learning-based Surrogate Model for Thermal Conductivity of Nanofluids
- Transfer learning for thermal conductivity
- 迁移学习用于热传导
-
Transfer learning of phase transitions in percolation and directed percolation
- Transfer learning of phase transitions in percolation and directed percolation
- 迁移学习用于precolation
-
Transfer learning for cancer diagnosis in histopathological images
- Transfer learning for cancer diagnosis
- 迁移学习用于癌症诊断
-
IEEE TASLP-22 Exploiting Adapters for Cross-lingual Low-resource Speech Recognition Zhihu article
- Cross-lingual speech recogntion using meta-learning and transfer learning
- 用元学习和迁移学习进行跨语言的低资源语音识别
-
More is Better: A Novel Multi-view Framework for Domain Generalization
- Multi-view learning for domain generalization
- 使用多视图学习来进行domain generalization
-
SLIP: Self-supervision meets Language-Image Pre-training
- Self-supervised learning + language image pretraining
- 用自监督学习用于语言到图像的预训练
-
Domain Prompts: Towards memory and compute efficient domain adaptation of ASR systems
- Prompt for domain adaptation in speech recognition
- 用Prompt在语音识别中进行domain adaptation
-
UMAD: Universal Model Adaptation under Domain and Category Shift
- Model adaptation under domain and category shift
- 在domain和class都有shift的前提下进行模型适配
-
Domain Adaptation on Point Clouds via Geometry-Aware Implicits
- Domain adaptation for point cloud
- 针对点云的domain adaptation
-
A Survey of Unsupervised Domain Adaptation for Visual Recognition
- A new survey article of domain adaptation
- 对UDA的一个综述文章，来自作者博士论文
-
VL-Adapter: Parameter-Efficient Transfer Learning for Vision-and-Language Tasks
- Vision-language efficient transfer learning
- 参数高校的vision-language任务迁移
-
Federated Learning with Adaptive Batchnorm for Personalized Healthcare
- Federated learning with adaptive batchnorm
- 用自适应BN进行个性化联邦学习
-
Unsupervised Domain Adaptation: A Reality Check
- Doing experiments to show the progress of DA methods over the years
- 用大量的实验来验证近几年来DA方法的进展
-
Hierarchical Optimal Transport for Unsupervised Domain Adaptation
- hierarchical optimal transport for UDA
- 层次性的最优传输用于domain adaptation
-
Unsupervised Domain Generalization by Learning a Bridge Across Domains
- Unsupervised domain generalization
- 无监督的domain generalization
-
Boosting Unsupervised Domain Adaptation with Soft Pseudo-label and Curriculum Learning
- Using soft pseudo-label and curriculum learning to boost UDA
- 用软的伪标签和课程学习增强UDA方法
-
Subtask-dominated Transfer Learning for Long-tail Person Search
- Subtask-dominated transfer for long-tail person search
- 子任务驱动的长尾人物搜索
-
Revisiting the Transferability of Supervised Pretraining: an MLP Perspective
- Revisit the transferability of supervised pretraining
- 重新思考有监督预训练的可迁移性
-
Multi-Agent Transfer Learning in Reinforcement Learning-Based Ride-Sharing Systems
- Multi-agent transfer in RL
- 在RL中的多智能体迁移
-
NeurIPS-21 On Learning Domain-Invariant Representations for Transfer Learning with Multiple Sources
- Theory and algorithm of domain-invariant learning for transfer learning
- 对invariant representation的理论和算法
-
WACV-22 Semi-supervised Domain Adaptation via Sample-to-Sample Self-Distillation
- Sample-level self-distillation for semi-supervised DA
- 样本层次的自蒸馏用于半监督DA
-
ROBIN : A Benchmark for Robustness to Individual Nuisancesin Real-World Out-of-Distribution Shifts
- A benchmark for robustness to individual OOD
- 一个OOD的benchmark
-
ICML-21 workshop Towards Principled Disentanglement for Domain Generalization
- Principled disentanglement for domain generalization
- Principled解耦用于domain generalization
-
NeurIPS-21 workshop CytoImageNet: A large-scale pretraining dataset for bioimage transfer learning
- A large-scale dataset for bioimage transfer learning
- 一个大规模的生物图像数据集用于迁移学习
-
NeurIPS-21 workshop Component Transfer Learning for Deep RL Based on Abstract Representations
- Deep transfer learning for RL
- 深度迁移学习用于强化学习
-
NeurIPS-21 workshop Maximum Mean Discrepancy for Generalization in the Presence of Distribution and Missingness Shift
- MMD for covariate shift
- 用MMD来解决covariate shift问题
-
Combined Scaling for Zero-shot Transfer Learning
- Scaling up for zero-shot transfer learning
- 增大训练规模用于zero-shot迁移学习
-
Federated Learning with Domain Generalization
- Federated domain generalization
- 联邦学习+domain generalization
-
Semi-Supervised Domain Generalization in Real World:New Benchmark and Strong Baseline
- Semi-supervised domain generalization
- 半监督+domain generalization
-
MICCAI-21 Domain Generalization for Mammography Detection via Multi-style and Multi-view Contrastive Learning
- Domain generalization for mammography detection
- 领域泛化用于乳房X射线检查
-
On Representation Knowledge Distillation for Graph Neural Networks
- Knowledge distillation for GNN
- 适用于GNN的知识蒸馏
-
BMVC-21 Domain Attention Consistency for Multi-Source Domain Adaptation
- Multi-source domain adaptation using attention consistency
- 用attention一致性进行多源的domain adaptation
-
Action Recognition using Transfer Learning and Majority Voting for CSGO
- Using transfer learning and majority voting for action recognition
- 使用迁移学习和多数投票进行动作识别
-
Open-Set Crowdsourcing using Multiple-Source Transfer Learning
- Open-set crowdsourcing using multiple-source transfer learning
- 使用多源迁移进行开放集的crowdsourcing
-
Improved Regularization and Robustness for Fine-tuning in Neural Networks
- Improve regularization and robustness for finetuning
- 针对finetune提高其正则和鲁棒性
-
TimeMatch: Unsupervised Cross-Region Adaptation by Temporal Shift Estimation
- Temporal domain adaptation
-
NeurIPS-21 Modular Gaussian Processes for Transfer Learning
- Modular Gaussian process for transfer learning
- 在迁移学习中使用modular Gaussian过程
-
Estimating and Maximizing Mutual Information for Knowledge Distillation
- Global and local mutual information maximation for knowledge distillation
- 局部和全局互信息最大化用于蒸馏
-
On Label Shift in Domain Adaptation via Wasserstein Distance
- Using Wasserstein distance to solve label shift in domain adaptation
- 在DA领域中用Wasserstein distance去解决label shift问题
-
Xi-Learning: Successor Feature Transfer Learning for General Reward Functions
- General reward function transfer learning in RL
- 在强化学习中general reward function的迁移学习
-
- Cross-modality domain adaptation for medical image segmentation
- 跨模态的DA用于医学图像分割
-
Deep Transfer Learning for Multi-source Entity Linkage via Domain Adaptation
- Domain adaptation for multi-source entiry linkage
- 用DA进行多源的实体链接
-
Temporal Knowledge Distillation for On-device Audio Classification
- Temporal knowledge distillation for on-device ASR
- 时序知识蒸馏用于设备端的语音识别
-
Transferring Domain-Agnostic Knowledge in Video Question Answering
- Domain-agnostic learning for VQA
- 在VQA任务中进行迁移学习
-
BMVC-21 SILT: Self-supervised Lighting Transfer Using Implicit Image Decomposition
- Lighting transfer using implicit image decomposition
- 用隐式图像分解进行光照迁移
-
Domain Adaptation in Multi-View Embedding for Cross-Modal Video Retrieval
- Domain adaptation for cross-modal video retrieval
- 用领域自适应进行跨模态的视频检索
-
Age and Gender Prediction using Deep CNNs and Transfer Learning
- Age and gender prediction using transfer learning
- 用迁移学习进行年龄和性别预测
-
Domain Adaptation for Rare Classes Augmented with Synthetic Samples
- Domain adaptation for rare class
- 稀疏类的domain adaptation
-
- Test-time adaptation for video semantic segmentation
- 测试时adaptation用于视频语义分割
-
NeurIPS-21 Unsupervised Domain Adaptation with Dynamics-Aware Rewards in Reinforcement Learning
- Domain adaptation in reinforcement learning
- 在强化学习中应用domain adaptation
-
- Domain generalization by audio-visual alignment
- 通过音频-视频对齐进行domain generalization
-
BMVC-21 Dynamic Feature Alignment for Semi-supervised Domain Adaptation
- Dynamic feature alignment for semi-supervised DA
- 动态特征对齐用于半监督DA
-
NeurIPS-21 FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling 知乎解读 code
- Curriculum pseudo label with a unified codebase TorchSSL
- 半监督方法FlexMatch和统一算法库TorchSSL
-
Rethinking supervised pre-training for better downstream transferring
- Rethink better finetune
- 重新思考预训练以便更好finetune
-
- Music sentiment transfer learning
- 迁移学习用于音乐sentiment
-
- Source-free domain adaptation using constrastive learning
- 无源域数据的DA，利用对比学习
-
Understanding Domain Randomization for Sim-to-real Transfer
- Understanding domain randomizationfor sim-to-real transfer
- 对强化学习中的sim-to-real transfer进行理论上的分析
-
Dynamically Decoding Source Domain Knowledge For Unseen Domain Generalization
- Ensemble learning for domain generalization
- 用集成学习进行domain generalization
-
Scale Invariant Domain Generalization Image Recapture Detection
- Scale invariant domain generalizaiton
- 尺度不变的domain generalization
-
IEEE TIP-21 Joint Clustering and Discriminative Feature Alignment for Unsupervised Domain Adaptation
- Clustering and discriminative alignment for DA
- 聚类与判定式对齐用于DA
-
IEEE TNNLS-21 Entropy Minimization Versus Diversity Maximization for Domain Adaptation
- Entropy minimization versus diversity max for DA
- 熵最小化与diversity最大化
-
Adversarial Domain Feature Adaptation for Bronchoscopic Depth Estimation
- Adversarial domain adaptation for bronchoscopic depth estimation
- 用对抗领域自适应进行支气管镜的深度估计
-
EMNLP-21 Few-Shot Intent Detection via Contrastive Pre-Training and Fine-Tuning
- Few-shot intent detection using pretrain and finetune
- 用迁移学习进行少样本意图检测
-
EMNLP-21 Non-Parametric Unsupervised Domain Adaptation for Neural Machine Translation
- UDA for machine translation
- 用领域自适应进行机器翻译
-
- Using Kronecker decomposition and knowledge distillation for pre-trained language models compression
- 用Kronecker分解和知识蒸馏来进行语言模型的压缩
-
Cross-Region Domain Adaptation for Class-level Alignment
- Cross-region domain adaptation for class-level alignment
- 跨区域的领域自适应用于类级别的对齐
-
- Domain adaptation for cross-modality liver segmentation
- 使用domain adaptation进行肝脏的跨模态分割
-
CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation
- Cross-domain transformer for domain adaptation
- 基于transformer进行domain adaptation
-
ICCV-21 Shape-Biased Domain Generalization via Shock Graph Embeddings
- Domain generalization based on shape information
- 基于形状进行domain generalization
-
Domain and Content Adaptive Convolution for Domain Generalization in Medical Image Segmentation
- Domain generalization for medical image segmentation
- 领域泛化用于医学图像分割
-
Class-conditioned Domain Generalization via Wasserstein Distributional Robust Optimization
- Domain generalization with wasserstein DRO
- 使用Wasserstein DRO进行domain generalization
-
FedZKT: Zero-Shot Knowledge Transfer towards Heterogeneous On-Device Models in Federated Learning
- Zero-shot transfer in heterogeneous federated learning
- 零次迁移用于联邦学习
-
Fishr: Invariant Gradient Variances for Out-of-distribution Generalization
- Invariant gradient variances for OOD generalization
- 不变梯度方差，用于OOD
-
How Does Adversarial Fine-Tuning Benefit BERT?
- Examine how does adversarial fine-tuning help BERT
- 探索对抗性finetune如何帮助BERT
-
Contrastive Domain Adaptation for Question Answering using Limited Text Corpora
- Contrastive domain adaptation for QA
- QA任务中应用对比domain adaptation
-
Robust Ensembling Network for Unsupervised Domain Adaptation
- Ensembling network for domain adaptation
- 集成嵌入网络用于domain adaptation
-
Federated Multi-Task Learning under a Mixture of Distributions
- Federated multi-task learning
- 联邦多任务学习
-
Fine-tuning is Fine in Federated Learning
- Finetuning in federated learning
- 在联邦学习中进行finetune
-
Federated Multi-Target Domain Adaptation
- Federated multi-target DA
- 联邦学习场景下的多目标DA
-
Learning Transferable Parameters for Unsupervised Domain Adaptation
- Learning partial transfer parameters for DA
- 学习适用于迁移部分的参数做UDA任务
-
MICCAI-21 A Systematic Benchmarking Analysis of Transfer Learning for Medical Image Analysis
- A benchmark of transfer learning for medical image
- 一个详细的迁移学习用于医学图像的benchmark
-
TVT: Transferable Vision Transformer for Unsupervised Domain Adaptation
- Vision transformer for domain adaptation
- 用视觉transformer进行DA
-
CIKM-21 AdaRNN: Adaptive Learning and Forecasting of Time Series Code 知乎文章 Video
- A new perspective to using transfer learning for time series analysis
- 一种新的建模时间序列的迁移学习视角
-
TKDE-21 Unsupervised Deep Anomaly Detection for Multi-Sensor Time-Series Signals
- Anomaly detection using semi-supervised and transfer learning
- 半监督学习用于无监督异常检测
-
SemDIAL-21 Generating Personalized Dialogue via Multi-Task Meta-Learning
- Generate personalized dialogue using multi-task meta-learning
- 用多任务元学习生成个性化的对话
-
ICCV-21 BiMaL: Bijective Maximum Likelihood Approach to Domain Adaptation in Semantic Scene Segmentation
- Bijective MMD for domain adaptation
- 双射MMD用于语义分割
-
A Survey on Cross-domain Recommendation: Taxonomies, Methods, and Future Directions
- A survey on cross-domain recommendation
- 跨领域的推荐的综述
-
A Data Augmented Approach to Transfer Learning for Covid-19 Detection
- Data augmentation to transfer learning for COVID
- 迁移学习使用数据增强，用于COVID-19
-
MM-21 Few-shot Unsupervised Domain Adaptation with Image-to-class Sparse Similarity Encoding
- Few-shot DA with image-to-class sparse similarity encoding
- 小样本的领域自适应
-
Dual-Tuning: Joint Prototype Transfer and Structure Regularization for Compatible Feature Learning
- Prototype transfer and structure regularization
- 原型的迁移学习
-
Finetuning Pretrained Transformers into Variational Autoencoders
- Finetune transformer to VAE
- 把transformer迁移到VAE
-
Pre-trained Models for Sonar Images
- Pre-trained models for sonar images
- 针对声纳图像的预训练模型
-
Domain Adaptor Networks for Hyperspectral Image Recognition
- Finetune for hyperspectral image recognition
- 针对高光谱图像识别的迁移学习
-
CVPR-21 Efficient Conditional GAN Transfer With Knowledge Propagation Across Classes
- Transfer conditional GANs to unseen classes
- 通过知识传递，迁移预训练的conditional GAN到新类别
-
CVPR-21 Ego-Exo: Transferring Visual Representations From Third-Person to First-Person Videos
- Transfer learning from third-person to first-person video
- 从第三人称视频迁移到第一人称
-
Toward Co-creative Dungeon Generation via Transfer Learning
- Game scene generation with transfer learning
- 用迁移学习生成游戏场景
-
Transfer Learning in Electronic Health Records through Clinical Concept Embedding
- Transfer learning in electronic health record
- 迁移学习用于医疗记录管理
-
CVPR-21 Conditional Bures Metric for Domain Adaptation
- A new metric for domain adaptation
- 提出一个新的metric用于domain adaptation
-
CVPR-21 Wasserstein Barycenter for Multi-Source Domain Adaptation
- Use Wasserstein Barycenter for multi-source domain adaptation
- 利用Wasserstein Barycenter进行DA
-
CVPR-21 Generalized Domain Adaptation
- A general definition for domain adaptation
- 一个更抽象更一般的domain adaptation定义
-
CVPR-21 Reducing Domain Gap by Reducing Style Bias
- Syle-invariant training for adaptation and generalization
- 通过训练图像对style无法辨别来进行DA和DG
-
CVPR-21 Uncertainty-Guided Model Generalization to Unseen Domains
- Uncertainty-guided generalization
- 基于不确定性的domain generalization
-
CVPR-21 Adaptive Methods for Real-World Domain Generalization
- Adaptive methods for domain generalization
- 动态算法，用于domain generalization
-
20210716 ICML-21 Continual Learning in the Teacher-Student Setup: Impact of Task Similarity
- Investigating task similarity in teacher-student learning
- 调研在continual learning下teacher-student learning问题的任务相似度
-
20210716 BMCV-extend Exploring Dropout Discriminator for Domain Adaptation
- Using multiple discriminators for domain adaptation
- 用分布估计代替点估计来做domain adaptation
-
20210716 TPAMI-21 Lifelong Teacher-Student Network Learning
- Lifelong distillation
- 持续的知识蒸馏
-
20210716 MICCAI-21 Few-Shot Domain Adaptation with Polymorphic Transformers
- Few-shot domain adaptation with polymorphic transformer
- 用多模态transformer做少样本的domain adaptation
-
20210716 InterSpeech-21 Speech2Video: Cross-Modal Distillation for Speech to Video Generation
- Cross-model distillation for video generation
- 跨模态蒸馏用于语音到video的生成
-
20210716 ICML-21 workshop Leveraging Domain Adaptation for Low-Resource Geospatial Machine Learning
- Using domain adaptation for geospatial ML
- 用domain adaptation进行地理空间的机器学习