Download
This repository implements Class Activation Mapping (CAM), a technique to expose the implicit attention of convolutional neural networks by generating heatmaps that highlight the most discriminative image regions influencing a network’s class prediction. The method involves modifying a CNN model slightly (e.g., using global average pooling before the final layer) to produce a weighted combination of feature maps as the class activation map. The repo provides example code and instructions for applying CAM to existing CNN architectures.
Features
- Generation of class activation heatmaps
- Integration with existing CNNs (with light modifications)
- Visualization of discriminative regions per class
- Ease of use / minimal code overhead
- Sample scripts / examples using standard architectures
- Works over multiple datasets / classes
Project Samples
Categories
Computer Vision LibrariesLicense
MIT LicenseFollow CAM
Other Useful Business Software
Our Free Plans just got better! | Auth0
You asked, we delivered! Auth0 is excited to expand our Free and Paid plans to include more options so you can focus on building, deploying, and scaling applications without having to worry about your security. Auth0 now, thank yourself later.
Rate This Project
Login To Rate This Project
User Reviews
Be the first to post a review of CAM!