Intentional Attention Mask Transformation for Robust CNN Classification

TL;DR

This paper introduces a multi-channel attention mechanism for CNNs that enhances interpretability by providing attribute-specific attention masks and improves robustness by emphasizing important features.

Contribution

The paper proposes a novel multi-channel attention mechanism that yields attribute-specific attention masks and enhances CNN robustness by focusing on key features.

Findings

Provides attribute-specific attention masks for CNN features

Improves CNN robustness by emphasizing important features

Achieves high interpretability and attribute recognition accuracy

Abstract

Convolutional Neural Networks have achieved impressive results in various tasks, but interpreting the internal mechanism is a challenging problem. To tackle this problem, we exploit a multi-channel attention mechanism in feature space. Our network architecture allows us to obtain an attention mask for each feature while existing CNN visualization methods provide only a common attention mask for all features. We apply the proposed multi-channel attention mechanism to multi-attribute recognition task. We can obtain different attention mask for each feature and for each attribute. Those analyses give us deeper insight into the feature space of CNNs. Furthermore, our proposed attention mechanism naturally derives a method for improving the robustness of CNNs. From the observation of feature space based on the proposed attention mask, we demonstrate that we can obtain robust CNNs by intentionally emphasizing features that are important for attributes. The experimental results for the benchmark dataset show that the proposed method gives high human interpretability while accurately grasping the attributes of the data, and improves network robustness.