CVPR2022 person re-identification

跨模态

1、Learning Memory-Augmented Unidirectional Metrics for Cross-modality Person Re-identification

2、FMCNet: Feature-Level Modality Compensation for Visible-Infrared Person Re-Identification

3、Learning Modal-Invariant and Temporal-Memory for Video-based Visible-Infrared Person Re-Identification

4、Learning with Twin Noisy Labels for Visible-Infrared Person Re-Identification

DG (domain generalization)

1、 Graph Sampling Based Deep Metric Learning for Generalizable Person Re-Identification
（廖老师的又一篇大作）

2、Cloning Outfits from Real-World Images to 3D Characters for Generalizable Person Re-Identification

3、Meta Distribution Alignment for Generalizable Person Re-Identification

4、AutoLoss-GMS: Searching Generalized Margin-based Softmax Loss Function for Person Re-identification

感觉今年的DG大受打击，看到挂在arxiv的好多DG reid论文都没中。。。。emmm
【私货】其他方向的DG论文，可借鉴
1、Domain-Aware Representation Learning for Unsupervised Domain Generalization

2、En-Compactness: Self-Distillation Embedding & Contrastive Generation for Generalized Zero-Shot Learning

3、Evading the Simplicity Bias: Training a Diverse Set of Models Discovers Solutions with Superior OOD Generalization

4、Amodal Segmentation through Out-of-Task and Out-of-Distribution Generalization with a Bayesian Model

5、Domain Generalization via Shuffled Style Assembly for Face Anti-Spoofing

6、Unsupervised Domain Generalization by learning a Bridge Across Domains

7、Causality Inspired Representation Learning for Domain Generalization

8、PCL: Proxy-based Contrastive Learning for Domain Generalization

9、On Generalizing Beyond Domains in Cross-Domain Continual Learning

10、The Two Dimensions of Worst-case Training and the Integrated Effect for Out-of-domain Generalization

11、Non-generative Generalized Zero-shot Learning via Task-correlated Disentanglement and Controllable Samples Synthesis

12、OoD-Bench: Quantifying and Understanding Two Dimensions of Out-of-Distribution Generalization

13、Meta Convolutional Neural Networks for Single Domain Generalization

14、Towards Principled Disentanglement for Domain Generalization

15、Distinguishing Unseen from Seen for Generalized Zero-shot Learning

16、Localized Adversarial Domain Generalization

17、Out-of-distribution Generalization with Causal Invariant Transformations

UDA (unsupervised domain adaptation)

1、Lifelong Unsupervised Domain Adaptive Person Re-identification with Coordinated Anti-forgetting and Adaptation

2、Unleashing Potential of Unsupervised Pre-Training with Intra-Identity Regularization for Person Re-Identification

完全无监督

1、Implicit Sample Extension for Unsupervised Person Re-Identification

2、Part-based Pseudo Label Refinement for Unsupervised Person Re-identification

知识蒸馏

1、Augmented Geometric Distillation for Data-Free Incremental Person ReID

2、

其他（换装、视频、遮挡、transformer等）

1、有监督：Camera-Conditioned Stable Feature Generation for Isolated Camera Supervised Person Re-IDentification

2、图像-视频：Temporal Complementarity-Guided Reinforcement Learning for Image-to-Video Person Re-Identification

3、视频：Salient-to-Broad Transition for Video Person Re-identification

4、换装：Learning Cloth-Irrelevant Features for Cloth-Changing Person Re-identification

5、Large scale pre-training for person re-identification with noisy labels

6、transformer：NFormer: Robust Person Re-identification with Neighbor Transformer

7、遮挡：Feature Erasing and Diffusion Network for Occluded Person Re-Identification

8、换装：Cloth-Changing Person Re-identification from A Single Image with Gait Prediction and Regularization