https://github.com/nicklhy/CAM

This demo shows the method proposed in "Zhou, Bolei, et al. "Learning Deep Features for Discriminative Localization." arXiv preprint arXiv:1512.04150 (2015)".
https://github.com/nicklhy/CAM

Last synced: 2 months ago
JSON representation

This demo shows the method proposed in "Zhou, Bolei, et al. "Learning Deep Features for Discriminative Localization." arXiv preprint arXiv:1512.04150 (2015)".

• Host: GitHub
• URL: https://github.com/nicklhy/CAM
• Owner: nicklhy
• Created: 2016-11-04T02:48:33.000Z (about 8 years ago)
• Default Branch: master
• Last Pushed: 2016-11-04T02:49:07.000Z (about 8 years ago)
• Last Synced: 2024-08-01T22:41:40.923Z (5 months ago)
• Language: Jupyter Notebook
• Size: 4.41 MB
• Stars: 9
• Watchers: 3
• Forks: 2
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• Awesome-MXNet - Class Activation Mapping

README

        
This demo shows the method proposed in "Zhou, Bolei, et al. "Learning Deep Features for Discriminative Localization." arXiv preprint arXiv:1512.04150 (2015)".

The proposed method can automatically localize the discriminative regions in an image using global average pooling

(GAP) in CNNs.

You can download the pretrained Inception-V3 network from [here](http://data.dmlc.ml/mxnet/models/imagenet/inception-v3.tar.gz). Other networks with similar structure(use global average pooling after the last conv feature map) should also work.