Graph-Attention Network with Adversarial Domain Alignment for Robust Cross-Domain Facial Expression Recognition

TL;DR

This paper introduces GAT-ADA, a hybrid framework combining graph attention and adversarial domain alignment to improve cross-domain facial expression recognition, achieving significant accuracy gains over baselines.

Contribution

It proposes a novel hybrid model that models inter-sample relations with graph attention and aligns domain distributions using adversarial and statistical methods.

Findings

Achieves 74.39% mean cross-domain accuracy

Reaches 98.0% accuracy on RAF-DB to FER2013 transfer

Improves by approximately 36 points over baseline methods

Abstract

Cross-domain facial expression recognition (CD-FER) remains difficult due to severe domain shift between training and deployment data. We propose Graph-Attention Network with Adversarial Domain Alignment (GAT-ADA), a hybrid framework that couples a ResNet-50 as backbone with a batch-level Graph Attention Network (GAT) to model inter-sample relations under shift. Each mini-batch is cast as a sparse ring graph so that attention aggregates cross-sample cues that are informative for adaptation. To align distributions, GAT-ADA combines adversarial learning via a Gradient Reversal Layer (GRL) with statistical alignment using CORAL and MMD. GAT-ADA is evaluated under a standard unsupervised domain adaptation protocol: training on one labeled source (RAF-DB) and adapting to multiple unlabeled targets (CK+, JAFFE, SFEW 2.0, FER2013, and ExpW). GAT-ADA attains 74.39% mean cross-domain accuracy. On RAF-DB to FER2013, it reaches 98.0% accuracy, corresponding to approximately a 36-point improvement over the best baseline we re-implemented with the same backbone and preprocessing.