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. The implementation is available <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup> .

Keywords

Computer scienceClass (philosophy)Convolutional neural networkDebuggingArtificial intelligenceProcess (computing)Machine learningArtificial neural networkPattern recognition (psychology)Programming language

Affiliated Institutions

Related Publications

Neural network ensembles

Several means for improving the performance and training of neural networks for classification are proposed. Crossvalidation is used as a tool for optimizing network parameters ...

1990 IEEE Transactions on Pattern Analysis... 4195 citations

Publication Info

Year
2020
Type
article
Citations
1186
Access
Closed

External Links

Social Impact

Social media, news, blog, policy document mentions

Citation Metrics

1186
OpenAlex

Cite This

Haofan Wang, Zifan Wang, Mengnan Du et al. (2020). Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks. . https://doi.org/10.1109/cvprw50498.2020.00020

Identifiers

DOI
10.1109/cvprw50498.2020.00020