学术搬砖 | Muyun99's wiki

学术搬砖: 论文阅读笔记

目录

# 1. 论文摘抄: 1-1. 论文中值得摘抄的句子 1-2. 论文常用表达 1-3. LaTeX常用表达 1-4. 论文阅读笔记范文 1-5. 可能会用到的表达 1-6. 撰写论文工具

# 2. 论文阅读-图像分类: 2-1. Query2Label A Simple Transformer Way to Multi-Label Classification 2-2. Contextual Transformer Networks for Visual Recognition 2-3. General Multi-label Image Classification with Transformers 2-4. RepVGG

# 3. 论文阅读-语义分割: 3-1. (DeepLabv1) Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs

# 4. 论文阅读-知识蒸馏: 4-1. Awesome-Knowledge-distillation

# 5. 论文阅读-Transformer: 5-1. Transformer系列代码 5-2. An Image is Worth 16x16 Words Transformers for Image Recognition at Scale 5-3. Do Vision Transformers See Like Convolutional Neural Networks

# 6. 论文阅读-图卷积网络: 6-1. Awesome-Graph-Neural-Network

# 7. 论文阅读-弱监督图像分割: 7-1. Awesome weakly supervised semantic segmentation 7-2. Self-supervised Equivariant Attention Mechanism for Weakly Supervised Semantic Segmentation 7-3. Weakly-Supervised Image Semantic Segmentation Using Graph Convolutional Networks 7-4. Discriminative Region Suppression for Weakly-Supervised Semantic Segmentation 7-5. Weakly-Supervised Semantic Segmentation via Sub-category Exploration 7-6. AffinityNet Learning Pixel level Semantic Affinity with Image level Supervision for Weakly Supervised Semantic Segmentation 7-7. Grad-CAM Visual Explanations from Deep Networks via Gradient-based Localization 7-8. Grad-CAM++ Improved Visual Explanations for Deep Convolutional Networks 7-9. Leveraging Auxiliary Tasks with Affinity Learning for Weakly Supervised Semantic Segmentation 7-10. Embedded Discriminative Attention Mechanism for Weakly Supervised Semantic Segmentation 7-11. Group-Wise Semantic Mining for Weakly Supervised Semantic Segmentation 7-12. Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentation 7-13. NoPeopleAllowed The Three-Step Approach to Weakly Supervised SemanticSegmentation 7-14. Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relations 7-15. Learning Deep Features for Discriminative Localization 7-16. Convolutional Random Walk Networks for Semantic Image Segmentation 7-17. Learning random-walk label propagation for weakly-supervised semantic segmentation 7-18. Puzzle-CAM Improved localization via matching partial and full features 7-19. Learning Visual Words for Weakly-Supervised Semantic Segmentation 7-20. 区域擦除 | Object Region Mining with Adversarial Erasing A Simple Classification to Semantic Segmentation Approach 7-21. CAM 扩散 | Tell Me Where to Look Guided Attention Inference Network 7-22. Self-Erasing Network for Integral Object Attention 7-23. Transformer CAM|Transformer Interpretability Beyond Attention Visualization 7-24. GETAM Gradient-weighted Element-wise Transformer Attention Map for Weakly-supervised Semantic segmentation 7-25. Class Re-Activation Maps for Weakly-Supervised Semantic Segmentation

# 8. 论文阅读-半监督图像分割: 8-1. Learning from Pixel-Level Label Noise A NewPerspective for Semi-Supervised SemanticSegmentation 8-2. Semi-supervised Semantic Segmentation via Strong-weak Dual-branch Network 8-3. Semi-Supervised Learning by exploiting unlabeled data correlations in a dual-branch network 8-4. DMT Dynamic Mutual Training for Semi-Supervised Learning 8-5. Semi-supervised semantic segmentation needs strong, varied perturbations 8-6. ClassMix Segmentation-Based Data Augmentation for Semi-Supervised Learning 8-7. Social-STGCNN A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Prediction 8-8. Semi-supevised Semantic Segmentation with High- and Low-level Consistency 8-9. Self-Tuning for Data-Efficient Deep Learning 8-10. FixMatch Simplifying Semi-Supervised Learning with Consistency and Confidence 8-11. Re-distributing Biased Pseudo Labels for Semi-supervised Semantic Segmentation A Baseline Investigation 8-12. Mean teachers are better role models Weight-averaged consistency targets improve semi-supervised deep learning results

# 9. 论文阅读-带噪学习

# 10. 论文阅读-小样本学习: 10-1. SPICE Semantic Pseudo-labeling for Image Clustering 10-2. Improving Unsupervised Image Clustering With Robust Learning 10-3. SCAN Learning to Classify Images without Labels 10-4. Sill-Net Feature Augmentation with Separated Illumination Representation

# 11. 论文阅读-自监督学习: 11-1. (MoCov1) Momentum Contrast for Unsupervised Visual Representation Learning 11-2. (SimCLRv1) A Simple Framework for Contrastive Learning of Visual Representations 11-3. (SimCLRv2) Big Self-Supervised Models are Strong Semi-Supervised Learners 11-4. (InstDis) Unsupervised Feature Learning via Non-Parametric Instance Discrimination 11-5. (CPC) Representation Learning with Contrastive Predictive Coding 11-6. (CMC) Contrastive Multiview Coding, also contains implementations for MoCo and InstDis 11-7. (HPT) Self-Supervised Pretraining Improves Self-Supervised Pretraining 11-8. (SimSiam) SimSiam Exploring Simple Siamese Representation Learning 11-9. 自监督系列代码

# 12. 语义分割中的知识蒸馏: 12-1. Structured Knowledge Distillation for Semantic Segmentation

# 13. 学术文章搜集: 13-1. Awesome-weakly-supervised-semantic-segmentation

# 14. 论文阅读-其他文章: 14-1. Decompose to Adapt Domain Disentanglement Faster-RCNN for Cross-domain Object Detection

上次更新: 2021/08/02, 21:04:52

学习笔记→

01
Structured Knowledge Distillation for Semantic Segmentation 06-03

02
README 美化 05-20

03
常见 Tricks 代码片段 05-12

更多文章>

×