Boosting Facial Expression Recognition by A Semi-Supervised Progressive Teacher

TL;DR

This paper introduces a semi-supervised learning algorithm called Progressive Teacher that enhances facial expression recognition by effectively utilizing both reliable labeled data and large-scale unlabeled images, improving accuracy and robustness.

Contribution

The proposed Progressive Teacher method automatically selects clean labeled samples and leverages unlabeled data, addressing label noise and data scarcity in in-the-wild FER datasets.

Findings

Achieves 89.57% accuracy on RAF-DB, surpassing previous methods.

Maintains performance with only 4.37% degradation at 30% synthetic noise.

Effectively utilizes unlabeled data to improve FER robustness.

Abstract

In this paper, we aim to improve the performance of in-the-wild Facial Expression Recognition (FER) by exploiting semi-supervised learning. Large-scale labeled data and deep learning methods have greatly improved the performance of image recognition. However, the performance of FER is still not ideal due to the lack of training data and incorrect annotations (e.g., label noises). Among existing in-the-wild FER datasets, reliable ones contain insufficient data to train robust deep models while large-scale ones are annotated in lower quality. To address this problem, we propose a semi-supervised learning algorithm named Progressive Teacher (PT) to utilize reliable FER datasets as well as large-scale unlabeled expression images for effective training. On the one hand, PT introduces semi-supervised learning method to relieve the shortage of data in FER. On the other hand, it selects useful labeled training samples automatically and progressively to alleviate label noise. PT uses selected clean labeled data for computing the supervised classification loss and unlabeled data for unsupervised consistency loss. Experiments on widely-used databases RAF-DB and FERPlus validate the effectiveness of our method, which achieves state-of-the-art performance with accuracy of 89.57% on RAF-DB. Additionally, when the synthetic noise rate reaches even 30%, the performance of our PT algorithm only degrades by 4.37%.