Semi-Supervised Facial Expression Recognition by Exploring False Pseudo-Labels

Hao Sun, Chenchen Pi, Wei XieICME 2023 · OpenReview

Abstract

Pseudo-labels are popular in semi-supervised facial expression recognition. Recent methods usually exploit the confidence as the criterion for pseudo-label generation, and utilize the high-confidence pseudo-labels as the ground-truth for training. However, high confidence cannot guarantee the correctness of pseudo-labels. False pseudo-labels can weaken the feature discrimination and degrade recognition performance. In this paper, we propose a Critical Feature Refinement Network (CFRN) to alleviate the interference of false pseudo-labels on the model performance. Specially, a feature dropout module and a feature emphasis module are proposed to improve the feature discrimination of CFRN. Then, a mean-absolute error loss is further exploited to improve the robustness against false pseudo-labels. Experimental results on three challenging datasets RAF-DB, SFEW and Affectnet demonstrate that the proposed CFRN outperforms the state-of-the-art methods.
BibTeX
@inproceedings{sun2023semi,
  author = {Hao Sun and Chenchen Pi and Wei Xie},
  title = {{Semi-Supervised Facial Expression Recognition by Exploring False Pseudo-Labels}},
  booktitle = {ICME},
  year = {2023},
  url = {https://openreview.net/forum?id=TbzbOahIZQ},
}

Loading related content...

Figure