# Score-CAM

**Repository Path**: finetooth/Score-CAM

## Basic Information

- **Project Name**: Score-CAM
- **Description**: [CVPRW 2020] Official implementation of Score-CAM in Pytorch
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 1
- **Created**: 2021-04-05
- **Last Updated**: 2022-12-18

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

## Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks
To appear at IEEE [CVPR 2020 Workshop on Fair, Data Efficient and Trusted Computer Vision](https://fadetrcv.github.io).

<img src="https://github.com/haofanwang/Score-CAM/blob/master/pics/comparison.png" width="100%" height="100%">

In this paper, we develop a novel post-hoc visual explanation method called Score-CAM based on class activation mapping. Score-CAM is a gradient-free visualization method, extended from Grad-CAM and Grad-CAM++. It achieves better visual performance and fairness for interpreting the decision making process. 

Paper: [Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks](http://openaccess.thecvf.com/content_CVPRW_2020/papers/w1/Wang_Score-CAM_Score-Weighted_Visual_Explanations_for_Convolutional_Neural_Networks_CVPRW_2020_paper.pdf) (Haofan Wang, Zifan Wang, Mengnan Du, Fan Yang, Zijian Zhang, Sirui Ding, Piotr Mardziel and Xia Hu.)

Demo [Colab](https://colab.research.google.com/drive/1m1VAhKaO7Jns5qt5igfd7lSVZudoKmID?usp=sharing)

## Update

**`2020.8.18`**: Score-CAM has been merged into [PaddlePaddle/InterpretDL](https://github.com/PaddlePaddle/InterpretDL).

**`2020.7.11`**: Score-CAM has been merged into [keisen/tf-keras-vis](https://github.com/keisen/tf-keras-vis).

**`2020.5.11`**: Score-CAM has been merged into [utkuozbulak/pytorch-cnn-visualizations](https://github.com/utkuozbulak/pytorch-cnn-visualizations).

**`2020.3.24`**: Score-CAM has been merged into [frgfm/torch-cam](https://github.com/frgfm/torch-cam).


## Citation
If you find this work or code is helpful in your research, please cite and star:
```
@inproceedings{wang2020score,
  title={Score-CAM: Score-weighted visual explanations for convolutional neural networks},
  author={Wang, Haofan and Wang, Zifan and Du, Mengnan and Yang, Fan and Zhang, Zijian and Ding, Sirui and Mardziel, Piotr and Hu, Xia},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  pages={24--25},
  year={2020}
}
```

## Thanks
Utils are built on [flashtorch](https://github.com/MisaOgura/flashtorch), thanks for releasing this great work!

## Contact
If you have any questions, feel free to contact me via: `haofanw@andrew.cmu.edu`