Rethinking the Learning Paradigm for Facial Expression Recognition
This addresses the challenge of noisy data in facial expression recognition, which is an incremental improvement in training methods for this domain.
The paper tackles the problem of ambiguous annotations in facial expression recognition datasets by proposing a shift from converting annotations to one-hot labels to using weakly supervised strategies that directly utilize the original ambiguous annotations.
Due to the subjective crowdsourcing annotations and the inherent inter-class similarity of facial expressions, the real-world Facial Expression Recognition (FER) datasets usually exhibit ambiguous annotation. To simplify the learning paradigm, most previous methods convert ambiguous annotation results into precise one-hot annotations and train FER models in an end-to-end supervised manner. In this paper, we rethink the existing training paradigm and propose that it is better to use weakly supervised strategies to train FER models with original ambiguous annotation.