/CAM

Class Activation Mapping

Primary LanguageC++

Sample code for the Class Activation Mapping

We propose a simple technique to expose the implicit attention of Convolutional Neural Networks on the image. It highlights the most informative image regions relevant to the predicted class. You could get attention-based model instantly by tweaking your own CNN a little bit more. The paper is published at CVPR'16.

The framework of the Class Activation Mapping is as below: Framework

Some predicted class activation maps are: Results

Pre-trained models:

Usage Instructions:

  • Install caffe, compile the matcaffe (matlab wrapper for caffe), and make sure you could run the prediction example code classification.m.
  • Clone the code from Github:
git clone https://github.com/metalbubble/CAM.git
cd CAM
  • Download the pretrained network
sh models/download.sh
  • Run the demo code to generate the heatmap: in matlab terminal,
demo
  • Run the demo code to generate bounding boxes from the heatmap: in matlab terminal,
generate_bbox

The demo video of what the CNN is looking is here. The reimplementation in tensorflow is here.

Reference:

@inproceedings{zhou2016cvpr,
    author    = {Zhou, Bolei and Khosla, Aditya and Lapedriza, Agata and Oliva, Aude and Torralba, Antonio},
    title     = {Learning Deep Features for Discriminative Localization},
    booktitle = {Computer Vision and Pattern Recognition},
    year      = {2016}
}

License:

The pre-trained models and the CAM technique are released for unrestricted use.

Contact Bolei Zhou if you have questions.