# Trend-Aware Supervision: On Learning Invariance for Semi-Supervised Facial Action Unit Intensity Estimation

arXiv: https://arxiv.org/abs/2503.08078 · HTML: https://mlsanity.com/paper/2503.08078/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 34 references that are in the map.
- First posted on arXiv 11 Mar 2025.

## Builds on (most cited first, 11 of 11)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [Semi-Supervised Learning with Ladder Networks](https://mlsanity.com/paper/1507.02672/) (2015)
- [Pyramid Feature Attention Network for Saliency detection](https://mlsanity.com/paper/1903.00179/) (2019)
- [Improving Multi-Task Generalization via Regularizing Spurious Correlation](https://mlsanity.com/paper/2205.09797/) (2022)
- [How Robust is Unsupervised Representation Learning to Distribution Shift?](https://mlsanity.com/paper/2206.08871/) (2022)
- [Deep Structured Learning for Facial Action Unit Intensity Estimation](https://mlsanity.com/paper/1704.04481/) (2017)
- [Joint Action Unit localisation and intensity estimation through heatmap regression](https://mlsanity.com/paper/1805.03487/) (2018)
- [DeepCoder: Semi-parametric Variational Autoencoders for Automatic Facial Action Coding](https://mlsanity.com/paper/1704.02206/) (2017)
- [Semi-supervised Facial Action Unit Intensity Estimation with Contrastive Learning](https://mlsanity.com/paper/2011.01864/) (2020)

## Abstract (arXiv)

With the increasing need for facial behavior analysis, semi-supervised AU intensity estimation using only keyframe annotations has emerged as a practical and effective solution to relieve the burden of annotation. However, the lack of annotations makes the spurious correlation problem caused by AU co-occurrences and subject variation much more prominent, leading to non-robust intensity estimation that is entangled among AUs and biased among subjects. We observe that trend information inherent in keyframe annotations could act as extra supervision and raising the awareness of AU-specific facial appearance changing trends during training is the key to learning invariant AU-specific features. To this end, we propose Trend-Aware Supervision (TAS), which pursues three kinds of trend awareness, including intra-trend ranking awareness, intra-trend speed awareness, and inter-trend subject awareness. TAS alleviates the spurious correlation problem by raising trend awareness during training to learn AU-specific features that represent the corresponding facial appearance changes, to achieve intensity estimation invariance. Experiments conducted on two commonly used AU benchmark datasets, BP4D and DISFA, show the effectiveness of each kind of awareness. And under trend-aware supervision, the performance can be improved without extra computational or storage costs during inference.