Deeply Explain CNN via Hierarchical Decomposition

Abstract

In computer vision, some attribution methods for explaining CNNs attempt to study how the intermediate features affect the network prediction. However, they usually ignore the feature hierarchies among the intermediate features. This paper introduces a hierarchical decomposition framework to explain CNN's decision-making process in a top-down manner. Specifically, we propose a gradient-based activation propagation (gAP) module that can decompose any intermediate CNN decision to its lower layers and find the supporting features. Then we utilize the gAP module to iteratively decompose the network decision to the supporting evidence from different CNN layers. The proposed framework can generate a deep hierarchy of strongly associated supporting evidence for the network decision, which provides insight into the decision-making process. Moreover, gAP is effort-free for understanding CNN-based models without network architecture modification and extra training process. Experiments show the effectiveness of the proposed method. The code and interactive demo website will be made publicly available.

References in corpus (6)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Explaining and Harnessing Adversarial Examples
• Understanding Neural Networks Through Deep Visualization
• Visualizing Deep Neural Network Decisions: Prediction Difference Analysis
• Understanding the Role of Individual Units in a Deep Neural Network
• Real Time Image Saliency for Black Box Classifiers

Cited by in corpus (1)

• Disentangled Explanations of Neural Network Predictions by Finding Relevant Subspaces