# objectdetection-saliency-maps
**Repository Path**: Ruoyu_chen/objectdetection-saliency-maps
## Basic Information
- **Project Name**: objectdetection-saliency-maps
- **Description**: Based on the mmdetection framework, compute various salience maps for object detection.
- **Primary Language**: Python
- **License**: Apache-2.0
- **Default Branch**: main
- **Homepage**: None
- **GVP Project**: No
## Statistics
- **Stars**: 0
- **Forks**: 0
- **Created**: 2022-10-30
- **Last Updated**: 2022-10-30
## Categories & Tags
**Categories**: Uncategorized
**Tags**: None
## README
# Object Detection Saliency Maps
Based on [mmdetection](https://github.com/open-mmlab/mmdetection) framework. You need to install MMDetaction first, follow here: [get_started.md](https://github.com/open-mmlab/mmdetection/blob/master/docs/en/get_started.md)
## 1. Grad-CAM
> Selvaraju, Ramprasaath R., et al. "Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization." International Journal of Computer Vision 128.2 (2020): 336-359.
Paper Url: [https://arxiv.org/abs/1610.02391](https://arxiv.org/abs/1610.02391)
Supported Object Detection Algorithm:
Yolo V3
Paper: [https://arxiv.org/abs/1804.02767](https://arxiv.org/abs/1804.02767)
Step by step see: [gradcam-yolov3.ipynb](tutorial/gradcam-yolov3.ipynb)
```angular2html
python gradcam-yolov3.py \
--config \
--checkpoint \
--image-path \
--bbox-index 0 \
--save-dir images/GradCAM/YOLOV3
```
Visualization:
|  |  |  |
| ---- | ---- | ---- |
|  |  |  |
## 2. D-RISE
> Vitali Petsiuk, Rajiv Jain, Varun Manjunatha, Vlad I. Morariu, Ashutosh Mehra, Vicente Ordonez, Kate Saenko; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, pp. 11443-11452
Paper Url: [https://openaccess.thecvf.com/content/CVPR2021/html/Petsiuk_Black-Box_Explanation_of_Object_Detectors_via_Saliency_Maps_CVPR_2021_paper.html](https://openaccess.thecvf.com/content/CVPR2021/html/Petsiuk_Black-Box_Explanation_of_Object_Detectors_via_Saliency_Maps_CVPR_2021_paper.html)
Supported Object Detection Algorithm:
Yolo V3
Paper: [https://arxiv.org/abs/1804.02767](https://arxiv.org/abs/1804.02767)
Step by step see: [drise-yolov3.ipynb](tutorial/drise-yolov3.ipynb)
```angular2html
python drise-yolov3.py \
--config \
--checkpoint \
--image-path \
--bbox-index 0 \
--save-dir images/DRISE/YOLOV3
```
Visualization:
|  |  |  |
| ---- | ---- | ---- |
|  |  |  |