# Noisy Student Training using Body Language Dataset Improves Facial Expression Recognition

arXiv: https://arxiv.org/abs/2008.02655 · HTML: https://mlsanity.com/paper/2008.02655/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Aug 2020.

## Built on by (most cited first, 8 of 8)

- [Facial expression and attributes recognition based on multi-task learning of lightweight neural networks](https://mlsanity.com/paper/2103.17107/) (2021)
- [Expression Snippet Transformer for Robust Video-based Facial Expression Recognition](https://mlsanity.com/paper/2109.08409/) (2021)
- [NR-DFERNet: Noise-Robust Network for Dynamic Facial Expression Recognition](https://mlsanity.com/paper/2206.04975/) (2022)
- [OmniLayout: Room Layout Reconstruction from Indoor Spherical Panoramas](https://mlsanity.com/paper/2104.09403/) (2021)
- [MIDAS: Mixing Ambiguous Data with Soft Labels for Dynamic Facial Expression Recognition](https://mlsanity.com/paper/2503.00202/) (2025)
- [BEE-NET: A deep neural network to identify in-the-wild Bodily Expression of Emotions](https://mlsanity.com/paper/2402.13955/) (2024)
- [Enhancing Ambiguous Dynamic Facial Expression Recognition with Soft Label-based Data Augmentation](https://mlsanity.com/paper/2506.20867/) (2025)
- [ARPGNet: Appearance- and Relation-aware Parallel Graph Attention Fusion Network for Facial Expression Recognition](https://mlsanity.com/paper/2511.22188/) (2025)

## Abstract (arXiv)

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.