https://github.com/raoyongming/CAL

[ICCV 2021] Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification
https://github.com/raoyongming/CAL

Last synced: about 2 months ago
JSON representation

[ICCV 2021] Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification

• Host: GitHub
• URL: https://github.com/raoyongming/CAL
• Owner: raoyongming
• License: mit
• Created: 2021-08-19T13:10:18.000Z (about 3 years ago)
• Default Branch: master
• Last Pushed: 2023-01-05T09:04:47.000Z (over 1 year ago)
• Last Synced: 2024-06-12T01:15:19.390Z (3 months ago)
• Language: Python
• Homepage:
• Size: 635 KB
• Stars: 142
• Watchers: 5
• Forks: 22
• Open Issues: 6
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• Vehicle_reID-Collection - code

README

        
# Counterfactual Attention Learning

Created by [Yongming Rao](https://raoyongming.github.io/)\*, [Guangyi Chen](https://chengy12.github.io/)\*, [Jiwen Lu](https://scholar.google.com/citations?user=TN8uDQoAAAAJ&hl=en&authuser=1), [Jie Zhou](https://scholar.google.com/citations?user=6a79aPwAAAAJ&hl=en&authuser=1)

This repository contains PyTorch implementation for ICCV 2021 paper __Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification__ [[arXiv]](https://arxiv.org/abs/2108.08728)

We propose to learn the attention with counterfactual causality, which provides a tool to measure the attention quality and a powerful supervisory signal to guide the learning process. 

![intro](figs/intro.png)

## CAL for Fine-Grained Visual Categorization

See [CAL-FGVC](fgvc/).

## CAL for Person Re-Identification

See [CAL-ReID](reid/).

## License

MIT License

## Citation

If you find our work useful in your research, please consider citing:

```

@inproceedings{rao2021counterfactual,

  title={Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification},

  author={Rao, Yongming and Chen, Guangyi and Lu, Jiwen and Zhou, Jie},

  booktitle={ICCV},

  year={2021}

}

```