Definition
CAM generates heatmaps overlaid on input images to show which pixels contributed most to the model’s decision for a particular class label. It works by applying global average pooling to the final convolutional feature maps, weighted by the importance of each map for the target class. This technique enhances model interpretability, allowing developers to debug biases, verify that models focus on relevant features rather than artifacts, and build trust in computer vision applications.
Summary
Class activation mapping (CAM) is a visualization technique that highlights the regions in an input image most responsible for a specific predicted class.
Key Concepts
- Heatmap Visualization
- Interpretability
- Feature Importance
- Global Average Pooling
Use Cases
- Medical image diagnosis verification
- Autonomous object detection debugging
- Explainable AI reporting