Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks

TL;DR

Score-CAM is a novel post-hoc visual explanation method for CNNs that improves interpretability by using class scores to weight activation maps, outperforming previous methods in recognition and localization tasks.

Contribution

It introduces a gradient-free approach for visual explanations, enhancing interpretability and fairness in CNN decision analysis.

Findings

Outperforms previous methods in recognition tasks

Achieves better localization accuracy

Passes sanity checks for explanation validity

Abstract

Recently, increasing attention has been drawn to the internal mechanisms of convolutional neural networks, and the reason why the network makes specific decisions. In this paper, we develop a novel post-hoc visual explanation method called Score-CAM based on class activation mapping. Unlike previous class activation mapping based approaches, Score-CAM gets rid of the dependence on gradients by obtaining the weight of each activation map through its forward passing score on target class, the final result is obtained by a linear combination of weights and activation maps. We demonstrate that Score-CAM achieves better visual performance and fairness for interpreting the decision making process. Our approach outperforms previous methods on both recognition and localization tasks, it also passes the sanity check. We also indicate its application as debugging tools. Official code has been released.