Skip to content
Code for the paper "Improving Pedestrian Attribute Recognition With Weakly-Supervised Multi-Scale Attribute-Specific Localization", ICCV 2019, http://arxiv.org/abs/1910.04562.
Python
Branch: master
Clone or download

Latest commit

Latest commit c1c757f Jan 30, 2020

Files

Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
model Delete .DS_Store Jan 30, 2020
utils Delete .DS_Store Jan 30, 2020
README.md update readme Jan 30, 2020
main.py update v1.0 Jan 30, 2020

README.md

Improving Pedestrian Attribute Recognition With Weakly-Supervised Multi-Scale Attribute-Specific Localization

Code for the paper "Improving Pedestrian Attribute Recognition With Weakly-Supervised Multi-Scale Attribute-Specific Localization", ICCV 2019, Seoul.

[Paper] [Poster]

Contact: chufeng.t@foxmail.com or tcf18@mails.tsinghua.edu.cn

Environment

  • Python 3.6+
  • PyTorch 0.4+

Datasets

The original datasets should be processed to match the DataLoader.

An example: dangweili/pedestrian-attribute-recognition-pytorch.

Training and Testing

python main.py --approach=inception_iccv --experiment=rap
python main.py --approach=inception_iccv --experiment=rap -e --resume='model_path'

Reference

If this work is useful to your research, please cite:

@inproceedings{tang2019improving,
  title={Improving Pedestrian Attribute Recognition With Weakly-Supervised Multi-Scale Attribute-Specific Localization},
  author={Tang, Chufeng and Sheng, Lu and Zhang, Zhaoxiang and Hu, Xiaolin},
  booktitle={Proceedings of the IEEE International Conference on Computer Vision},
  pages={4997--5006},
  year={2019}
}
You can’t perform that action at this time.