Attention Branch Network: Learning of Attention Mechanism for Visual Explanation

TL;DR

The paper introduces the Attention Branch Network (ABN), a novel model that integrates an attention mechanism for improved image recognition and visual explanation, demonstrating superior performance across multiple tasks.

Contribution

It proposes ABN, a new end-to-end trainable architecture that combines attention mechanisms with visual explanation for enhanced CNN performance.

Findings

ABN outperforms baseline models in image classification.

ABN generates effective attention maps for visual explanation.

ABN improves accuracy in fine-grained and facial attribute recognition.

Abstract

Visual explanation enables human to understand the decision making of Deep Convolutional Neural Network (CNN), but it is insufficient to contribute the performance improvement. In this paper, we focus on the attention map for visual explanation, which represents high response value as the important region in image recognition. This region significantly improves the performance of CNN by introducing an attention mechanism that focuses on a specific region in an image. In this work, we propose Attention Branch Network (ABN), which extends the top-down visual explanation model by introducing a branch structure with an attention mechanism. ABN can be applicable to several image recognition tasks by introducing a branch for attention mechanism and is trainable for the visual explanation and image recognition in end-to-end manner. We evaluate ABN on several image recognition tasks such as image classification, fine-grained recognition, and multiple facial attributes recognition. Experimental results show that ABN can outperform the accuracy of baseline models on these image recognition tasks while generating an attention map for visual explanation. Our code is available at https://github.com/machine-perception-robotics-group/attention_branch_network.