Code for our CVPR 2021 paper "MetaCam+DSCE"

Joint Noise-Tolerant Learning and Meta Camera Shift Adaptation for Unsupervised Person Re-Identification (CVPR'21)

Introduction

Code for our CVPR 2021 paper "MetaCam+DSCE".

Prerequisites

• CUDA>=10.0

• At least two 1080-Ti GPUs

• Other necessary packages listed in requirements.txt

• Training Data

  (Market-1501, DukeMTMC-reID and MSMT-17. You can download these datasets from Zhong's repo)

  Unzip all datasets and ensure the file structure is as follow:

  MetaCam_DSCE/data    
  │
  └───market1501 OR dukemtmc OR msmt17
       │   
       └───DukeMTMC-reID OR Market-1501-v15.09.15 OR MSMT17_V1
           │   
           └───bounding_box_train
           │   
           └───bounding_box_test
           | 
           └───query
           │   
           └───list_train.txt (only for MSMT-17)
           | 
           └───list_query.txt (only for MSMT-17)
           | 
           └───list_gallery.txt (only for MSMT-17)
           | 
           └───list_val.txt (only for MSMT-17)
  

Usage

See run.sh for details.

Acknowledgments

This repo borrows partially from MWNet (meta-learning), ECN (exemplar memory) and SpCL (faiss-based acceleration). If you find our code useful, please cite their papers.

@inproceedings{shu2019meta,
  title={Meta-Weight-Net: Learning an Explicit Mapping For Sample Weighting},
  author={Shu, Jun and Xie, Qi and Yi, Lixuan and Zhao, Qian and Zhou, Sanping and Xu, Zongben and Meng, Deyu},
  booktitle={NeurIPS},
  year={2019}
}

@inproceedings{zhong2019invariance,
  title={Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-identification},
  author={Zhong, Zhun and Zheng, Liang and Luo, Zhiming and Li, Shaozi and Yang, Yi},
  booktitle={CVPR},
  year={2019},
}

@inproceedings{ge2020selfpaced,
    title={Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID},
    author={Yixiao Ge and Feng Zhu and Dapeng Chen and Rui Zhao and Hongsheng Li},
    booktitle={NeurIPS},
    year={2020}
}

Citation

@inproceedings{yang2021meta,
  title={Joint Noise-Tolerant Learning and Meta Camera Shift Adaptation for Unsupervised Person Re-Identification},
  author={Yang, Fengxiang and Zhong, Zhun and Luo, Zhiming and Cai, Yuanzheng and Li, Shaozi and Nicu, Sebe},
  booktitle={CVPR},
  year={2021},
}

Resources

1. Pre-trained MMT-500 models to reproduce Tab. 3 of our paper. BaiduNetDisk, Passwd: nsbv. Google Drive.

2. Pedestrian images used to plot Fig.3 in our paper. BaiduNetDisk, Passwd: ydrf. Google Drive.

   Please download 'marCam' and 'dukeCam', put them under 'MetaCam_DSCE/data' and uncomment corresponding code. (e.g., L#87-89, L#163-168 of train_usl_knn_merge.py)

Contact Us

Email: [email protected]