AU-Supervised Convolutional Vision Transformers for Synthetic Facial Expression Recognition

TL;DR

This paper introduces AU-Supervised Convolutional Vision Transformers (AU-CVT), a novel framework that leverages AU information and synthetic data to improve facial expression recognition performance in-the-wild.

Contribution

The paper proposes a new AU-supervised vision transformer model that enhances FER by integrating AU labels and synthetic data, with transfer learning from face recognition.

Findings

Achieved F1 score of 0.6863 on validation set

Achieved accuracy of 0.7433 on validation set

Demonstrated improved FER performance using AU supervision

Abstract

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