Facial Expression Recognition with Mid-Level Representation Enhancement and Graph Embedded Uncertainty Suppressing

Abstract

Facial expression is an essential factor in conveying human emotional states and intentions. Although remarkable advancement has been made in facial expression recognition (FER) tasks, challenges due to large variations of expression patterns and unavoidable data uncertainties remain. In this paper, we propose mid-level representation enhancement (MRE) and graph embedded uncertainty suppressing (GUS) addressing these issues. On one hand, MRE is introduced to avoid expression representation learning being dominated by a limited number of highly discriminative patterns. On the other hand, GUS is introduced to suppress the feature ambiguity in the representation space. The proposed method not only has stronger generalization capability to handle different variations of expression patterns but also more robustness in capturing expression representations. Experimental evaluation on Aff-Wild2 have verified the effectiveness of the proposed method. We achieved 2nd place in the Learning from Synthetic Data (LSD) Challenge of the 4th Competition on Affective Behavior Analysis in-the-wild (ABAW). The code has been released at https://github.com/CruiseYuGH/GUS .