Cluster-CAM: Cluster-Weighted Visual Interpretation of CNNs' Decision in Image Classification

TL;DR

Cluster-CAM is a novel gradient-free visualization method for CNNs that efficiently produces accurate heatmaps by clustering feature maps, improving interpretability and reducing computation time.

Contribution

This paper introduces Cluster-CAM, a new unsupervised clustering approach that significantly enhances the speed and clarity of CNN decision visualizations compared to existing methods.

Findings

Cluster-CAM produces heatmaps aligning well with human cognition.

It reduces the number of forward passes needed for interpretation.

Experimental results show superior effectiveness and efficiency over existing CAMs.

Abstract

Despite the tremendous success of convolutional neural networks (CNNs) in computer vision, the mechanism of CNNs still lacks clear interpretation. Currently, class activation mapping (CAM), a famous visualization technique to interpret CNN's decision, has drawn increasing attention. Gradient-based CAMs are efficient while the performance is heavily affected by gradient vanishing and exploding. In contrast, gradient-free CAMs can avoid computing gradients to produce more understandable results. However, existing gradient-free CAMs are quite time-consuming because hundreds of forward interference per image are required. In this paper, we proposed Cluster-CAM, an effective and efficient gradient-free CNN interpretation algorithm. Cluster-CAM can significantly reduce the times of forward propagation by splitting the feature maps into clusters in an unsupervised manner. Furthermore, we propose an artful strategy to forge a cognition-base map and cognition-scissors from clustered feature maps. The final salience heatmap will be computed by merging the above cognition maps. Qualitative results conspicuously show that Cluster-CAM can produce heatmaps where the highlighted regions match the human's cognition more precisely than existing CAMs. The quantitative evaluation further demonstrates the superiority of Cluster-CAM in both effectiveness and efficiency.