SOTAVerified

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

2019-10-03Code Available0· sign in to hype

Haofan Wang, Zifan Wang, Mengnan Du, Fan Yang, Zijian Zhang, Sirui Ding, Piotr Mardziel, Xia Hu

Code Available — Be the first to reproduce this paper.

Reproduce

Code

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.

Tasks

Benchmark Results

DatasetModelMetricClaimedVerifiedStatus
CUB-200-2011Score-CAMAverage highest confidence (ResNet-101)0.25Unverified
CUB-200-2011 (ResNet-101)Score-CAMAverage highest confidence0.25Unverified

Reproductions