# Semantic Neighborhood-Aware Deep Facial Expression Recognition

arXiv: https://arxiv.org/abs/2004.12725 · HTML: https://mlsanity.com/paper/2004.12725/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Apr 2020.

## Built on by (most cited first, 5 of 5)

- [FERV39k: A Large-Scale Multi-Scene Dataset for Facial Expression Recognition in Videos](https://mlsanity.com/paper/2203.09463/) (2022)
- [Affect Expression Behaviour Analysis in the Wild using Consensual Collaborative Training](https://mlsanity.com/paper/2107.05736/) (2021)
- [Dynamic Adaptive Threshold based Learning for Noisy Annotations Robust Facial Expression Recognition](https://mlsanity.com/paper/2208.10221/) (2022)
- [Monotonic Kolmogorov-Arnold Networks: A Theoretical and Empirical Study of Monotonicity as an Inductive Bias](https://mlsanity.com/paper/2606.17886/) (2026)
- [Consensual Collaborative Training And Knowledge Distillation Based Facial Expression Recognition Under Noisy Annotations](https://mlsanity.com/paper/2107.04746/) (2021)

## Abstract (arXiv)

Different from many other attributes, facial expression can change in a continuous way, and therefore, a slight semantic change of input should also lead to the output fluctuation limited in a small scale. This consistency is important. However, current Facial Expression Recognition (FER) datasets may have the extreme imbalance problem, as well as the lack of data and the excessive amounts of noise, hindering this consistency and leading to a performance decreasing when testing. In this paper, we not only consider the prediction accuracy on sample points, but also take the neighborhood smoothness of them into consideration, focusing on the stability of the output with respect to slight semantic perturbations of the input. A novel method is proposed to formulate semantic perturbation and select unreliable samples during training, reducing the bad effect of them. Experiments show the effectiveness of the proposed method and state-of-the-art results are reported, getting closer to an upper limit than the state-of-the-art methods by a factor of 30% in AffectNet, the largest in-the-wild FER database by now.