Automatically understanding emotions from visual data is a fundamental task for human behaviour understanding. While models devised for Facial Expression Recognition (FER) have demonstrated excellent performances on many datasets, they often suffer from severe performance degradation when trained and tested on different datasets due to domain shift. In addition, as face images are considered highly sensitive data, the accessibility to large-scale datasets for model training is often denied. In this work, we tackle the above-mentioned problems by proposing the first Source-Free Unsupervised Domain Adaptation (SFUDA) method for FER. Our method exploits self-supervised pretraining to learn good feature representations from the target data and proposes a novel and robust cluster-level pseudo-labelling strategy that accounts for in-cluster statistics. We validate the effectiveness of our method in four adaptation setups, proving that it consistently outperforms existing SFUDA methods when applied to FER, and is on par with methods addressing FER in the UDA setting.

This work was supported by the EU JPI/CH SHIELD project, by the PRIN project PREVUE (Prot. 2017N2RK7K), the EU H2020 MARVEL (957337) project, the EU ISFP PROTECTOR (101034216) project, the EU H2020 SPRING project (871245), and by Fondazione VRT. It was carried out under the "Vision and Learning joint Laboratory" between FBK and UNITN.