# Auditing Demographic Bias in Facial Landmark Detection for Fair Human-Robot Interaction

arXiv: https://arxiv.org/abs/2604.06961 · HTML: https://mlsanity.com/paper/2604.06961/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 23 references that are in the map.
- First posted on arXiv 8 Apr 2026.

## Builds on (most cited first, 9 of 9)

- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Look at Boundary: A Boundary-Aware Face Alignment Algorithm](https://mlsanity.com/paper/1805.10483/) (2018)
- [Analysis of Gender Inequality In Face Recognition Accuracy](https://mlsanity.com/paper/2002.00065/) (2020)
- [Characterizing the Variability in Face Recognition Accuracy Relative to Race](https://mlsanity.com/paper/1904.07325/) (2019)
- [Multi-task head pose estimation in-the-wild](https://mlsanity.com/paper/2202.02299/) (2022)
- [On the representation and methodology for wide and short range head pose estimation](https://mlsanity.com/paper/2401.05807/) (2024)
- [Fairness and Bias in Robot Learning](https://mlsanity.com/paper/2207.03444/) (2022)
- [Hierarchical Attention-based Age Estimation and Bias Estimation](https://mlsanity.com/paper/2103.09882/) (2021)
- [Face Recognition In Children: A Longitudinal Study](https://mlsanity.com/paper/2204.01760/) (2022)

## Abstract (arXiv)

Fairness in human-robot interaction critically depends on the reliability of the perceptual models that enable robots to interpret human behavior. While demographic biases have been widely studied in high-level facial analysis tasks, their presence in facial landmark detection remains unexplored. In this paper, we conduct a systematic audit of demographic bias in this task, analyzing the age, gender, and race biases. To this end, we introduce a controlled statistical methodology to disentangle demographic effects from confounding visual factors. Our analysis demonstrates that visual confounders, particularly head pose and face resolution, heavily outweigh the impact of demographic attributes. Notably, after accounting for these confounders, performance disparities across gender and race vanish. However, we identify a statistically significant age-related bias, with higher localization errors for older individuals. This shows that fairness issues can emerge even in low-level vision components and can propagate through the HRI pipeline. We argue that auditing and correcting such biases is a necessary step toward trustworthy and equitable robot perception systems.