Skip to content

Incremental Generative Occlusion Adversarial Suppression Network for Person ReID (IEEE T-IP 2021)

License

Notifications You must be signed in to change notification settings

Vill-Lab/2021-TIP-IGOAS

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

39 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

PWC

Incremental Generative Occlusion Adversarial Suppression Network for Person ReID (IEEE T-IP 2021)

This is the pytorch implementation of the paper (accpted by IEEE TIP 2021). More information about the paper is in here. Chinese introduction can be clicked here.

Fig 1.IGOAS framework

Installation

Make sure conda is installed.

# cd to your preferred directory and clone this repo
git clone https://github.com/Vill-Lab/IGOAS.git
cd IGOAS

# create environment
conda create --name torchreid python=3.7
conda activate torchreid

# install dependencies
# make sure `which python` and `which pip` point to the correct path
pip install -r requirements.txt

# install torch and torchvision (select the proper cuda version to suit your machine)
conda install pytorch torchvision cudatoolkit=9.0 -c pytorch

# install torchreid (don't need to re-build it if you modify the source code)
python setup.py develop

Training

To train IGOAS on Occluded-Duke, do

 python scripts/main.py --config-file configs/bfe.yaml

Result

Method Rank-1 mAP
PGFA 51.4 37.3
HONet 55.1 43.8
MHSA 59.7 44.8
IGOAS 60.1 49.4

Citation

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

@article{tip21igoas,
   author = {Zhao, Cairong and Lv, Xinbi and Dou, Shuguang and Zhang, Shanshan and Wu, Jun and Wang, Liang},
   title = {Incremental Generative Occlusion Adversarial Suppression Network for Person ReID},
   journal = {IEEE Transactions on Image Processing},
   volume = {30},
   pages = {4212-4224},
   DOI = {10.1109/tip.2021.3070182},
   url = {<Go to ISI>://MEDLINE:33822724},
   year = {2021},
   type = {Journal Article}
}

Reference

This code is based on torchreid.

About

Incremental Generative Occlusion Adversarial Suppression Network for Person ReID (IEEE T-IP 2021)

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages