A Multi-task Mean Teacher for Semi-supervised Facial Affective Behavior Analysis
This work addresses a domain-specific problem for human-computer interaction researchers by providing an incremental improvement in semi-supervised learning for facial affective behavior analysis.
The paper tackled the problem of incomplete labeled datasets in multi-task affective behavior recognition by proposing a semi-supervised model using a mean teacher framework to leverage unlabeled data, achieving much better performance than baselines and ranking 4th in two competition tracks and 6th in another.
Affective Behavior Analysis is an important part in human-computer interaction. Existing multi-task affective behavior recognition methods suffer from the problem of incomplete labeled datasets. To tackle this problem, this paper presents a semi-supervised model with a mean teacher framework to leverage additional unlabeled data. To be specific, a multi-task model is proposed to learn three different kinds of facial affective representations simultaneously. After that, the proposed model is assigned to be student and teacher networks. When training with unlabeled data, the teacher network is employed to predict pseudo labels for student network training, which allows it to learn from unlabeled data. Experimental results showed that our proposed method achieved much better performance than baseline model and ranked 4th in both competition track 1 and track 2, and 6th in track 3, which verifies that the proposed network can effectively learn from incomplete datasets.