📓Personal notes of Papers
여기에 쓰인 사진들은 전부 해당 논문에서 인용해온 것들
- Improved Techniques for Training GANs
- Image-to-Image Translation with Conditional Adversarial Networks
- Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
- Recurrent Models of Visual Attention
- Attention Is All You Need
- Looking at Vehicles on the Road: A Survey of Vision-Based Vehicle Detection, Tracking, and Behavior Analysis
- Large Scale Distributed Deep Networks
- Overcoming catastrophic forgetting in neural networks
- Squeeze-and-Excitation Networks
- Continual Learning with Deep Generative Replay
- Cross-Domain Self-supervised Multi-task Feature Learning using Synthetic Imagery
- Mix-and-Match Tuning for Self-Supervised Semantic Segmentation
- CyCADA: Cycle-Consistent Adversarial Domain Adaptation
- Learning to Adapt Structured Output Space for Semantic Segmentation
- Adversarial Discriminative Domain Adaptation
- Weakly Supervised Action Localization by Sparse Temporal Pooling Network
- Two-Stream Convolutional Networks for Action Recognition in Videos
- Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset
- Tell Me When to Change Lanes: Learning to interpret side-rear view
- What do Deep Networks Like to See?
- Prototypical Networks for Few-shot Learning
- Multiple Instance Detection Network with Online Instance Classifier Refinement
- Boosting Self-Supervised Learning via Knowledge Transfer
- End-to-end Learning of Image based Lane-Change Decision [note]
- Learning Deep Features for Discriminative Localization [note]
- Network in Network
- Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps [simple note]
- Is object localization for free? - Weakly-supervised learning with convolutional neural network
- Hide-and-Seek: Forcing a Network to be Meticulous for Weakly-supervised Object and Action Localization [simple note]
- Weakly Supervised Deep Detection Networks
- Object Detectors Emerge in Deep Scene CNNs
- DOCK: Detecting Objects by transferring Common-sense Knowledge
- LSDA: Large Scale Detection Through Adaptation
- Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
- Training Deep Neural Networks on Imbalanced Data Sets
- Transferring Knowledge to smaller network with class-distance loss [note]
- A Unified Framework for Tumor Proliferation Score Prediction in Breast Histopathology [note]