Proceedings

Towards Regularized Mixture of Predictions for Class-Imbalanced Semi-Supervised Facial Expression Recognition

Hangyu Li, Yixin Zhang, Jiangchao Yao, Nannan Wang, Bo Han

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Main Track. Pages 1377-1385.

https://doi.org/10.24963/ijcai.2025/154

Keywords

  • Computer Vision: CV: Transfer, low-shot, semi- and un- supervised learning
  • Computer Vision: CV: Biometrics, face, gesture and pose recognition
  • Humans and AI: HAI: Human-computer interaction

Abstract

Semi-supervised facial expression recognition (SSFER) effectively assigns pseudo-labels to confident unlabeled samples when only limited emotional annotations are available. Existing SSFER methods are typically built upon an assumption of the class-balanced distribution. However, they are far from real-world applications due to biased pseudo-labels caused by class imbalance. To alleviate this issue, we propose Regularized Mixture of Predictions (ReMoP), a simple yet effective method to generate high-quality pseudo-labels for imbalanced samples. Specifically, we first integrate feature similarity into the linear prediction to learn a mixture of predictions. Furthermore, we introduce a class regularization term that constrains the feature geometry to mitigate imbalance bias. Being practically simple, our method can be integrated with existing semi-supervised learning and SSFER methods to tackle the challenge associated with class-imbalanced SSFER effectively. Extensive experiments on four facial expression datasets demonstrate the effectiveness of the proposed method across various imbalanced conditions. The source code is made publicly available at https://github.com/hangyu94/ReMoP.

Hangyu Li, Yixin Zhang, Jiangchao Yao, Nannan Wang, and Bo Han. 2025. Towards Regularized Mixture of Predictions for Class-Imbalanced Semi-Supervised Facial Expression Recognition. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 1377–1385. https://doi.org/10.24963/ijcai.2025/154
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards