# Adaptive Graph-Based Feature Normalization for Facial Expression Recognition

arXiv: https://arxiv.org/abs/2207.11123 · HTML: https://mlsanity.com/paper/2207.11123/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 29 references that are in the map.
- First posted on arXiv 22 Jul 2022.

## Builds on (most cited first, 14 of 14)

- [Monte Carlo Gradient Estimation in Machine Learning](https://mlsanity.com/paper/1906.10652/) (2019)
- [Learning from Noisy Labels with Distillation](https://mlsanity.com/paper/1703.02391/) (2017)
- [Training Deep Networks for Facial Expression Recognition with Crowd-Sourced Label Distribution](https://mlsanity.com/paper/1608.01041/) (2016)
- [Region Attention Networks for Pose and Occlusion Robust Facial Expression Recognition](https://mlsanity.com/paper/1905.04075/) (2019)
- [CurriculumNet: Weakly Supervised Learning from Large-Scale Web Images](https://mlsanity.com/paper/1808.01097/) (2018)
- [TransFER: Learning Relation-aware Facial Expression Representations with Transformers](https://mlsanity.com/paper/2108.11116/) (2021)
- [Neural Ranking Models with Weak Supervision](https://mlsanity.com/paper/1704.08803/) (2017)
- [Emotion Recognition in Speech using Cross-Modal Transfer in the Wild](https://mlsanity.com/paper/1808.05561/) (2018)
- [Feature Decomposition and Reconstruction Learning for Effective Facial Expression Recognition](https://mlsanity.com/paper/2104.05160/) (2021)
- [Covariance Pooling For Facial Expression Recognition](https://mlsanity.com/paper/1805.04855/) (2018)
- [FaceNet2ExpNet: Regularizing a Deep Face Recognition Net for Expression Recognition](https://mlsanity.com/paper/1609.06591/) (2016)
- [Peak-Piloted Deep Network for Facial Expression Recognition](https://mlsanity.com/paper/1607.06997/) (2016)
- [Learning Grimaces by Watching TV](https://mlsanity.com/paper/1610.02255/) (2016)
- [Avoiding Your Teacher's Mistakes: Training Neural Networks with Controlled Weak Supervision](https://mlsanity.com/paper/1711.00313/) (2017)

## Abstract (arXiv)

Facial Expression Recognition (FER) suffers from data uncertainties caused by ambiguous facial images and annotators' subjectiveness, resulting in excursive semantic and feature covariate shifting problem. Existing works usually correct mislabeled data by estimating noise distribution, or guide network training with knowledge learned from clean data, neglecting the associative relations of expressions. In this work, we propose an Adaptive Graph-based Feature Normalization (AGFN) method to protect FER models from data uncertainties by normalizing feature distributions with the association of expressions. Specifically, we propose a Poisson graph generator to adaptively construct topological graphs for samples in each mini-batches via a sampling process, and correspondingly design a coordinate descent strategy to optimize proposed network. Our method outperforms state-of-the-art works with accuracies of 91.84% and 91.11% on the benchmark datasets FERPlus and RAF-DB, respectively, and when the percentage of mislabeled data increases (e.g., to 20%), our network surpasses existing works significantly by 3.38% and 4.52%.