Poly-cam: high resolution class activation map for convolutional neural networks

Abstract

The demand for explainable AI continues to rise alongside advancements in deep learning technology. Existing methods such as convolutional neural networks often struggle to accurately pinpoint the image features justifying a network’s prediction due to low-resolution saliency maps (e.g., CAM), smooth visualizations from perturbation-based techniques, or numerous isolated peaky spots in gradient-based approaches. In response, our work seeks to merge information from earlier and later layers within the network to create high-resolution class activation maps that not only maintain a level of competitiveness with previous art in terms of insertion-deletion faithfulness metrics but also significantly surpass it regarding the precision in localizing class-specific features.