https://github.com/ashok-arjun/cnn-explainer
Techniques for interpreting ConvNets
https://github.com/ashok-arjun/cnn-explainer
convnets convolutional-neural-networks deep-learning interpretability
Last synced: over 1 year ago
JSON representation
Techniques for interpreting ConvNets
- Host: GitHub
- URL: https://github.com/ashok-arjun/cnn-explainer
- Owner: ashok-arjun
- Created: 2020-08-28T10:14:05.000Z (almost 6 years ago)
- Default Branch: master
- Last Pushed: 2020-12-21T10:26:41.000Z (over 5 years ago)
- Last Synced: 2025-01-30T17:39:33.903Z (over 1 year ago)
- Topics: convnets, convolutional-neural-networks, deep-learning, interpretability
- Language: Python
- Homepage:
- Size: 11.6 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# CNN-Explainer
This repository implements the following techniques for interpreting convolutional neural networks:
1. Saliency maps [1]
2. Guided Backpropagation [2]
3. Class visualization [3]
4. Grad-CAM [4]
Apart from this, the following techniques are also implemented
1. Adversarial fooling (by backpropagating gradients w.r.t. to classification error of required fooling class into the image) [5]
## References
1. Simonyan, K. et al. “Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps.” CoRR abs/1312.6034 (2014): n. pag.
2. Springenberg, Jost Tobias et al. “Striving for Simplicity: The All Convolutional Net.” CoRR abs/1412.6806 (2015): n. pag.
3. Yosinski, J. et al. “Understanding Neural Networks Through Deep Visualization.” ArXiv abs/1506.06579 (2015): n. pag.
4. Selvaraju, R. R. et al. “Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization.” International Journal of Computer Vision 128 (2019): 336-359.
5. Szegedy, Christian et al. “Intriguing properties of neural networks.” CoRR abs/1312.6199 (2014): n. pag.