AU-Guided Unsupervised Domain Adaptive Facial Expression Recognition
This work provides an incremental improvement for researchers and practitioners working on facial expression recognition by improving model adaptability across different datasets.
This paper addresses the challenge of domain diversity in facial expression recognition (FER) datasets by proposing an AU-guided unsupervised Domain Adaptive FER (AdaFER) framework. The method leverages facial action unit (AU) detection to guide annotation transfer from source to target domains and employs AU-guided triplet training to learn domain-invariant features, achieving state-of-the-art results on multiple benchmarks.
The domain diversities including inconsistent annotation and varied image collection conditions inevitably exist among different facial expression recognition (FER) datasets, which pose an evident challenge for adapting the FER model trained on one dataset to another one. Recent works mainly focus on domain-invariant deep feature learning with adversarial learning mechanism, ignoring the sibling facial action unit (AU) detection task which has obtained great progress. Considering AUs objectively determine facial expressions, this paper proposes an AU-guided unsupervised Domain Adaptive FER (AdaFER) framework to relieve the annotation bias between different FER datasets. In AdaFER, we first leverage an advanced model for AU detection on both source and target domain. Then, we compare the AU results to perform AU-guided annotating, i.e., target faces that own the same AUs with source faces would inherit the labels from source domain. Meanwhile, to achieve domain-invariant compact features, we utilize an AU-guided triplet training which randomly collects anchor-positive-negative triplets on both domains with AUs. We conduct extensive experiments on several popular benchmarks and show that AdaFER achieves state-of-the-art results on all these benchmarks.