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.
Contact: chufeng.t@foxmail.com or tcf18@mails.tsinghua.edu.cn
- Python 3.6+
- PyTorch 0.4+
- RAP: http://rap.idealtest.org/
- PETA: http://mmlab.ie.cuhk.edu.hk/projects/PETA.html
- PA-100K: https://github.com/xh-liu/HydraPlus-Net
The original datasets should be processed to match the DataLoader.
We provide the label lists for training and testing.
python main.py --approach=inception_iccv --experiment=rap
python main.py --approach=inception_iccv --experiment=rap -e --resume='model_path'
We provide the pretrained models for reference, the results may slightly different with the values reported in our paper.
Dataset | mA | Link |
---|---|---|
PETA | 86.34 | Model |
RAP | 81.86 | Model |
PA-100K | 80.45 | Model |
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}
}