# Fighting noise and imbalance in Action Unit detection problems

arXiv: https://arxiv.org/abs/2303.02994 · HTML: https://mlsanity.com/paper/2303.02994/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 22 references that are in the map.
- First posted on arXiv 6 Mar 2023.

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

- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics](https://mlsanity.com/paper/1705.07115/) (2017)
- [VGGFace2: A dataset for recognising faces across pose and age](https://mlsanity.com/paper/1710.08092/) (2017)
- [Going deeper with Image Transformers](https://mlsanity.com/paper/2103.17239/) (2021)
- [Does label smoothing mitigate label noise?](https://mlsanity.com/paper/2003.02819/) (2020)
- [JhatAA-Net: Joint Facial Action Unit Detection and Face Alignment via Adaptive Attention](https://mlsanity.com/paper/2003.08834/) (2020)
- [Deep Adaptive Attention for Joint Facial Action Unit Detection and Face Alignment](https://mlsanity.com/paper/1803.05588/) (2018)
- [Facial Action Unit Detection Using Attention and Relation Learning](https://mlsanity.com/paper/1808.03457/) (2018)
- [Deep Structure Inference Network for Facial Action Unit Recognition](https://mlsanity.com/paper/1803.05873/) (2018)
- [Multi-Order Networks for Action Unit Detection](https://mlsanity.com/paper/2202.00446/) (2022)
- [Privileged Attribution Constrained Deep Networks for Facial Expression Recognition](https://mlsanity.com/paper/2203.12905/) (2022)

## Abstract (arXiv)

Action Unit (AU) detection aims at automatically caracterizing facial expressions with the muscular activations they involve. Its main interest is to provide a low-level face representation that can be used to assist higher level affective computing tasks learning. Yet, it is a challenging task. Indeed, the available databases display limited face variability and are imbalanced toward neutral expressions. Furthermore, as AU involve subtle face movements they are difficult to annotate so that some of the few provided datapoints may be mislabeled. In this work, we aim at exploiting label smoothing ability to mitigate noisy examples impact by reducing confidence [1]. However, applying label smoothing as it is may aggravate imbalance-based pre-existing under-confidence issue and degrade performance. To circumvent this issue, we propose Robin Hood Label Smoothing (RHLS). RHLS principle is to restrain label smoothing confidence reduction to the majority class. In that extent, it alleviates both the imbalance-based over-confidence issue and the negative impact of noisy majority class examples. From an experimental standpoint, we show that RHLS provides a free performance improvement in AU detection. In particular, by applying it on top of a modern multi-task baseline we get promising results on BP4D and outperform state-of-the-art methods on DISFA.