AU-Supervised Convolutional Vision Transformers for Synthetic Facial Expression Recognition
This work addresses the problem of learning from synthetic data for facial expression recognition, which is important for applications in affective computing, but it appears incremental as it builds on existing methods with AU supervision.
The paper tackled synthetic facial expression recognition by using AU-supervised convolutional vision transformers to improve performance, achieving an F1 score of 0.6863 and accuracy of 0.7433 on a validation set.
The paper describes our proposed methodology for the six basic expression classification track of Affective Behavior Analysis in-the-wild (ABAW) Competition 2022. In Learing from Synthetic Data(LSD) task, facial expression recognition (FER) methods aim to learn the representation of expression from the artificially generated data and generalise to real data. Because of the ambiguous of the synthetic data and the objectivity of the facial Action Unit (AU), we resort to the AU information for performance boosting, and make contributions as follows. First, to adapt the model to synthetic scenarios, we use the knowledge from pre-trained large-scale face recognition data. Second, we propose a conceptually-new framework, termed as AU-Supervised Convolutional Vision Transformers (AU-CVT), which clearly improves the performance of FER by jointly training auxiliary datasets with AU or pseudo AU labels. Our AU-CVT achieved F1 score as $0.6863$, accuracy as $0.7433$ on the validation set. The source code of our work is publicly available online: https://github.com/msy1412/ABAW4