AUCH-Net: Action Unit-Based Consistency-Aware Hypergraph Network for Cross-Domain Few-Shot Facial Expression Recognition

2026-07-23

AI Summary

This work addresses the challenge of cross-domain few-shot facial expression recognition, where large domain discrepancies and scarce target samples hinder effective transferable feature learning. To tackle this, the study introduces action unit (AU) semantics into the task for the first time and proposes a consistency-aware hypergraph network. By leveraging AU-guided feature learning and incorporating both relation consistency loss and AU regularization loss, the method models fine-grained associations between AUs and expression categories within a hypergraph structure, effectively bridging the gap between subtle facial movements and high-level semantic expressions. Extensive experiments demonstrate that the proposed approach significantly outperforms state-of-the-art methods on both laboratory-controlled and real-world datasets, validating the efficacy and superiority of AU-based relational modeling under cross-domain few-shot settings.

Abstract

Recently, cross-domain few-shot facial expression recognition (CF-FER) has received considerable attention. However, the performance of existing CF-FER methods is still unsatisfactory due to inferior transferable feature learning under large domain discrepancy and limited target samples. Fortunately, the action units (AUs), which indicate the movements of different facial muscles, provide consistent conceptual semantics for describing expressions within and across domains. Inspired by this, we propose a novel Action Unit-based Consistency-aware Hypergraph Network (AUCH-Net), which constructs consistency-aware hypergraphs on AUs, for CF-FER. Specifically, AUCH-Net presents a new AU feature learning (AFL) module and a new visual feature learning (VFL) module. The AFL module learns AU features under the guidance of a novel relation consistency loss and an AU regularization loss, while the VFL module learns visual features supervised by a relation consistency loss and a classification loss. By learning consistent AU features, AUCH-Net effectively models the connections between AUs and expression categories. As a result, we can bridge the gap between fine-grained facial variations and high-level expression categories, greatly facilitating the learning of transferable feature representations.Extensive experiments on both in-the-lab and in-the-wild datasets show that our method consistently outperforms several state-of-the-art methods. Our results clearly show that modeling the relationships among AUs holds significant potential for FER under cross-domain few-shot scenarios.

Problem

• cross-domain
• few-shot
• facial expression recognition
• action units
• transferable features

Innovation

• Action Units
• Consistency-aware Hypergraph
• Cross-domain Few-shot Learning
• Facial Expression Recognition
• Relation Consistency Loss