Learn To Pay Attention

TL;DR

This paper introduces an end-to-end trainable attention module for CNNs that highlights relevant image regions, improves classification accuracy across multiple datasets, and enhances robustness against adversarial attacks.

Contribution

The paper presents a novel attention module integrated into CNNs, enabling better focus on important image regions and improving generalization and robustness.

Findings

Attention maps highlight relevant regions and suppress background clutter.

Improved classification accuracy on 6 unseen benchmark datasets.

Enhanced robustness against adversarial attacks.

Abstract

We propose an end-to-end-trainable attention module for convolutional neural network (CNN) architectures built for image classification. The module takes as input the 2D feature vector maps which form the intermediate representations of the input image at different stages in the CNN pipeline, and outputs a 2D matrix of scores for each map. Standard CNN architectures are modified through the incorporation of this module, and trained under the constraint that a convex combination of the intermediate 2D feature vectors, as parameterised by the score matrices, must \textit{alone} be used for classification. Incentivised to amplify the relevant and suppress the irrelevant or misleading, the scores thus assume the role of attention values. Our experimental observations provide clear evidence to this effect: the learned attention maps neatly highlight the regions of interest while suppressing background clutter. Consequently, the proposed function is able to bootstrap standard CNN architectures for the task of image classification, demonstrating superior generalisation over 6 unseen benchmark datasets. When binarised, our attention maps outperform other CNN-based attention maps, traditional saliency maps, and top object proposals for weakly supervised segmentation as demonstrated on the Object Discovery dataset. We also demonstrate improved robustness against the fast gradient sign method of adversarial attack.