Skip to content

Latest commit

 

History

History
38 lines (25 loc) · 1.37 KB

README.md

File metadata and controls

38 lines (25 loc) · 1.37 KB
Raw

Salience-Guided Iterative Asymmetric Mutual Hashing for Fast Person Re-Identification (IEEE TIP 2021)

This is the pytorch implementation of the paper (accepted by IEEE TIP 2021).

Fig 1.SIAMH framework

Training

Training details for differnet lenght of hash codes are shown in the folder of training logs.

Pretrained-weights: https://pan.baidu.com/s/16UZK6i45r56MkOL95a3zKg (1aiv)

To train/evaluate SIAMH onMarket-1501, do

python tools/train_net.py --config-file configs/Market1501/myconfig.yml --teacher-config-file configs_teacher/Market1501/myconfig.yml  

python tools/train_net.py --config-file configs/Market1501/myconfig.yml --teacher-config-file configs_teacher/Market1501/myconfig.yml --eval-only MODEL.WEIGHTS /path/to/checkpoint_file

Citation

If you find SIAMH useful in your research, please consider citing.

@article{zhao2021salience,
  title={Salience-guided iterative asymmetric mutual hashing for fast person re-identification},
  author={Zhao, Cairong and Tu, Yuanpeng and Lai, Zhihui and Shen, Fumin and Shen, Heng Tao and Miao, Duoqian},
  journal={IEEE Transactions on Image Processing},
  volume={30},
  pages={7776--7789},
  year={2021},
  publisher={IEEE}
}

Reference

This code is based on torchreid.