Global Multiple Extraction Network for Low-Resolution Facial Expression Recognition

TL;DR

This paper introduces GME-Net, a novel network designed to improve low-resolution facial expression recognition by combining local detail extraction with global feature modeling, outperforming existing methods.

Contribution

The paper presents a new global multiple extraction network that effectively captures discriminative features in low-resolution facial images, addressing limitations of existing approaches.

Findings

GME-Net outperforms existing methods on multiple datasets.

The hybrid attention and multi-scale modules enhance feature extraction.

The approach improves recognition accuracy in low-resolution scenarios.

Abstract

Facial expression recognition, as a vital computer vision task, is garnering significant attention and undergoing extensive research. Although facial expression recognition algorithms demonstrate impressive performance on high-resolution images, their effectiveness tends to degrade when confronted with low-resolution images. We find it is because: 1) low-resolution images lack detail information; 2) current methods complete weak global modeling, which make it difficult to extract discriminative features. To alleviate the above issues, we proposed a novel global multiple extraction network (GME-Net) for low-resolution facial expression recognition, which incorporates 1) a hybrid attention-based local feature extraction module with attention similarity knowledge distillation to learn image details from high-resolution network; 2) a multi-scale global feature extraction module with quasi-symmetric structure to mitigate the influence of local image noise and facilitate capturing global image features. As a result, our GME-Net is capable of extracting expression-related discriminative features. Extensive experiments conducted on several widely-used datasets demonstrate that the proposed GME-Net can better recognize low-resolution facial expression and obtain superior performance than existing solutions.