DR-FER: Discriminative and Robust Representation Learning for Facial Expression Recognition

• Main Authors: LI, Ming, FU, Huazhu, HE, Shengfeng, FAN, Hehe, LIU, Jun, KEPPO, Jussi, SHOU, Mike Zheng
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2023
• Subjects: Annotations; Artificial neural networks; Electronic mail; Facial expression recognition; masked image modeling; Representation learning; Schedules; self-paced learning; Task analysis; Training; Databases and Information Systems; Graphics and Human Computer Interfaces
• Online Access: https://ink.library.smu.edu.sg/sis_research/8635
• Institution: Singapore Management University

Learning discriminative and robust representations is important for facial expression recognition (FER) due to subtly different emotional faces and their subjective annotations. Previous works usually address one representation solely because these two goals seem to be contradictory for optimization. Their performances inevitably suffer from challenges from the other representation. In this paper, by considering this problem from two novel perspectives, we demonstrate that discriminative and robust representations can be learned in a unified approach, i.e. DR-FER, and mutually benefit each other. Moreover, we make it with the supervision from only original annotations. Specifically, to learn discriminative representations, we propose performing masked image modeling (MIM) as an auxiliary task to force our network to discover expression-related facial areas. This is the first attempt to employ MIM to explore discriminative patterns in a self-supervised manner. To extract robust representations, we present a category-aware self-paced learning schedule to mine high-quality annotated ( easy ) expressions and incorrectly annotated ( hard ) counterparts. We further introduce a retrieval similarity-based relabeling strategy to correct hard expression annotations, exploiting them more effectively. By enhancing the discrimination ability of the FER classifier as a bridge, these two learning goals significantly strengthen each other. Extensive experiments on several popular benchmarks demonstrate the superior performance of our DR-FER. Moreover, thorough visualizations and extra experiments on manually annotation-corrupted datasets show that our approach successfully accomplishes learning both discriminative and robust representations simultaneously.