Batch Transformer: Look for Attention in Batch

TL;DR

This paper introduces a batch transformer network with class batch attention and multi-level attention mechanisms to improve facial expression recognition by leveraging batch information and capturing multi-level feature correlations, outperforming existing methods.

Contribution

The paper proposes a novel batch transformer architecture with class batch attention and multi-level attention to enhance FER performance on noisy data, addressing overfitting and feature correlation issues.

Findings

Outperforms state-of-the-art FER methods on benchmark datasets.

Effectively handles noisy and uncertain FER images.

Demonstrates robustness across various challenging conditions.

Abstract

Facial expression recognition (FER) has received considerable attention in computer vision, with "in-the-wild" environments such as human-computer interaction. However, FER images contain uncertainties such as occlusion, low resolution, pose variation, illumination variation, and subjectivity, which includes some expressions that do not match the target label. Consequently, little information is obtained from a noisy single image and it is not trusted. This could significantly degrade the performance of the FER task. To address this issue, we propose a batch transformer (BT), which consists of the proposed class batch attention (CBA) module, to prevent overfitting in noisy data and extract trustworthy information by training on features reflected from several images in a batch, rather than information from a single image. We also propose multi-level attention (MLA) to prevent overfitting the specific features by capturing correlations between each level. In this paper, we present a batch transformer network (BTN) that combines the above proposals. Experimental results on various FER benchmark datasets show that the proposed BTN consistently outperforms the state-ofthe-art in FER datasets. Representative results demonstrate the promise of the proposed BTN for FER.