Leveraging Synthetic Data for Generalizable and Fair Facial Action Unit Detection

arXiv:2403.10737v1 Announce Type: new
Abstract: Facial action unit (AU) detection is a fundamental block for objective facial expression analysis. Supervised learning approaches require a large amount of manual labeling which is costly. The limited labeled data are also not diverse in terms of gender which can affect model fairness. In this paper, we propose to use synthetically generated data and multi-source domain adaptation (MSDA) to address the problems of the scarcity of labeled data and the diversity of subjects. Specifically, …

abstract analysis arxiv block cs.cv data detection diverse fair fairness gender labeling supervised learning synthetic synthetic data terms type