This repository is the official implementation of our paper "Hard-sample Guided Hybrid Contrast Learning for Unsupervised Person Re-Identification!".
git clone https://github.com/bupt-ai-cz/HHCL-ReID.git
cd HHCL-ReID
pip install -r requirements.txt
python setup.py develop
Download the datasets Market-1501,MSMT17,DukeMTMC-reID from this link and unzip them under the directory like:
HHCL-ReID/examples/data
├── market1501
│ └── Market-1501-v15.09.15
└── dukemtmcreid
└── DukeMTMC-reID
Prepare ImageNet Pre-trained Models for IBN-Net
When training with the backbone of IBN-ResNet, you need to download the ImageNet-pretrained model from this link and save it under the path of examples/pretrained/.
HHCL-ReID/examples
└── pretrained
└── resnet50_ibn_a.pth.tar
We utilize 4 GTX-2080TI GPUs for training. Examples:
Market-1501:
CUDA_VISIBLE_DEVICES=0,1,2,3 python examples/train.py -b 256 -a resnet50 -d market1501 --iters 200 --eps 0.45 --momentum 0.1 --num-instances 16 --pooling-type avg --memorybank CMhybird --epochs 60 --logs-dir examples/logs/market1501/resnet50_avg_cmhybird
DukeMTMC-reID:
CUDA_VISIBLE_DEVICES=0,1,2,3 python examples/train.py -b 256 -a resnet50 -d dukemtmcreid --iters 200 --eps 0.6 --momentum 0.1 --num-instances 16 --pooling-type avg --memorybank CMhybird --epochs 60 --logs-dir examples/logs/dukemtmcreid/resnet50_avg_cmhybird
- use
-a resnet50(default) for the backbone of ResNet-50, and-a resnet_ibn50afor the backbone of IBN-ResNet; - use
--pooling-type gemfor Generalized Mean Pooling (GEM) pooling and--smoothfor label smoothing.
To evaluate my model on ImageNet, run:
CUDA_VISIBLE_DEVICES=0 python examples/test.py -d $DATASET --resume $PATH --pooling-type avg
Our model achieves the following performance on :
| Dataset | Market1501 | DukeMTMC-reID | ||||||
|---|---|---|---|---|---|---|---|---|
| Setting | mAP | R1 | R5 | R10 | mAP | R1 | R5 | R10 |
| Fully Unsupervised | 84.2 | 93.4 | 97.7 | 98.5 | 73.3 | 85.1 | 92.4 | 94.6 |
| Supervised | 87.2 | 94.6 | 98.5 | 99.1 | 80.0 | 89.8 | 95.2 | 96.7 |
You can download the above models in the paper from [Google Drive]
If you find this code useful for your research, please cite our paper
@article{hu2021hard,
title={Hard-sample Guided Hybrid Contrast Learning for Unsupervised Person Re-Identification},
author={Hu, Zheng and Zhu, Chuang and He, Gang},
journal={arXiv preprint arXiv:2109.12333},
year={2021}
}
This project is not possible without multiple great opensourced codebases. We list them below.
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent