Home

Awesome

LUPerson

Unsupervised Pre-training for Person Re-identification (LUPerson).

PWC PWC PWC PWC

The repository is for our CVPR2021 paper Unsupervised Pre-training for Person Re-identification.

LUPerson Dataset

LUPerson is currently the largest unlabeled dataset for Person Re-identification, which is used for Unsupervised Pre-training. LUPerson consists of 4M images of over 200K identities and covers a much diverse range of capturing environments.

LUPerson can only be used for research, commercial usage is forbidden.

Details can be found at ./LUP.

Pre-trained Models

Modelpath
ResNet50R50
ResNet101R101
ResNet152R152

Finetuned Results

For MGN with ResNet50:

DatasetmAPcmc1path
MSMT1766.06/79.9385.08/87.63MSMT
DukeMTMC82.27/91.7090.35/92.82Duke
Market150191.12/96.1696.26/97.12Market
CUHK03-L74.54/85.8474.64/82.86CUHK03

These numbers are a little different from those reported in our paper, and most are slightly better.

For MGN with ResNet101:

DatasetmAPcmc1path
MSMT1768.41/81.1286.28/88.27-
DukeMTMC84.15/92.7791.88/93.99-
Market150191.86/96.2196.56/97.03-
CUHK03-L75.98/86.7375.86/84.07-

The numbers are in the format of without RR/with RR.

Citation

If you find this code useful for your research, please cite our paper.

@article{fu2020unsupervised,
  title={Unsupervised Pre-training for Person Re-identification},
  author={Fu, Dengpan and Chen, Dongdong and Bao, Jianmin and Yang, Hao and Yuan, Lu and Zhang, Lei and Li, Houqiang and Chen, Dong},
  journal={Proceedings of the IEEE conference on computer vision and pattern recognition},
  year={2021}
}

News

We extend our LUPerson to LUPerson-NL with Noisy Labels which are generated from tracking algorithm, Please check for our CVPR22 paper Large-Scale Pre-training for Person Re-identification with Noisy Labels. And LUPerson-NL dataset is available at https://github.com/DengpanFu/LUPerson-NL

Third-party Usage

LUPerson and LUPerson-NL are used by some work and have obtained very good performance.