MDM: Multiple Dynamic Masks for Visual Explanation of Neural Networks

TL;DR

This paper introduces MDM, a learning-based method for generating class activation maps that is general, high-performing, and applicable across various neural network architectures, improving interpretability and explainability.

Contribution

The paper proposes MDM, a novel dynamic masking algorithm that enhances CAM generation's generality and performance, surpassing existing methods and applicable to different neural network models.

Findings

MDM achieves state-of-the-art CAM performance.

Applying MDM improves interpretability of neural networks.

MDM enhances explainable prototype search in ProtoPNet and XProtoNet.

Abstract

The Class Activation Map (CAM) lookup of a neural network tells us to which regions the neural network focuses when it makes a decision. In the past, the CAM search method was dependent upon a specific internal module of the network. It has specific constraints on the structure of the neural network. To make the search of CAM have generality and high performance. We propose a learning-based algorithm, namely Multiple Dynamic Masks (MDM). It is based on a public cognition that only active features of a picture related to classification will affect the classification results of the neural network, and other features will hardly affect the classification results of the network. The mask generated by MDM conforms to the above cognition. It trains mask vectors of different sizes by constraining mask values and activating consistency, then it uses stacking masks of different scale to generate CAM that can balance spatial information and semantic information. Comparing the results of MDM with those of the recent advanced CAM search method, the performance of MDM has reached the state of the art results. We applied the MDM method to the interpretable neural networks ProtoPNet and XProtoNet, which improved the performance of model in the explainable prototype search. Finally, we visualized the CAM generation effect of MDM on neural networks of different architectures, verifying the generality of the MDM method.