Noisy Student Training using Body Language Dataset Improves Facial Expression Recognition
This work addresses data inadequacy in facial expression recognition for applications in human-computer interaction, but it is incremental as it builds on existing noisy student training and attention mechanisms.
The paper tackles the challenge of facial expression recognition from videos with limited labeled data by using a self-training method with a labeled dataset and an unlabeled body language dataset (BoLD), achieving state-of-the-art performance on benchmark datasets CK+ and AFEW 8.0 compared to other single models.
Facial expression recognition from videos in the wild is a challenging task due to the lack of abundant labelled training data. Large DNN (deep neural network) architectures and ensemble methods have resulted in better performance, but soon reach saturation at some point due to data inadequacy. In this paper, we use a self-training method that utilizes a combination of a labelled dataset and an unlabelled dataset (Body Language Dataset - BoLD). Experimental analysis shows that training a noisy student network iteratively helps in achieving significantly better results. Additionally, our model isolates different regions of the face and processes them independently using a multi-level attention mechanism which further boosts the performance. Our results show that the proposed method achieves state-of-the-art performance on benchmark datasets CK+ and AFEW 8.0 when compared to other single models.