Towards Fair Affective Robotics: Continual Learning for Mitigating Bias in Facial Expression and Action Unit Recognition

TL;DR

This paper explores using Continual Learning to improve fairness in facial expression and action unit recognition, addressing demographic bias issues in affective robotics.

Contribution

It introduces CL-based strategies as a novel approach to mitigate bias in FER systems and demonstrates their superior performance over existing methods.

Findings

CL methods outperform traditional bias mitigation techniques

Experiments conducted on RAF-DB and BP4D benchmarks

CL enhances fairness in affective recognition systems

Abstract

As affective robots become integral in human life, these agents must be able to fairly evaluate human affective expressions without discriminating against specific demographic groups. Identifying bias in Machine Learning (ML) systems as a critical problem, different approaches have been proposed to mitigate such biases in the models both at data and algorithmic levels. In this work, we propose Continual Learning (CL) as an effective strategy to enhance fairness in Facial Expression Recognition (FER) systems, guarding against biases arising from imbalances in data distributions. We compare different state-of-the-art bias mitigation approaches with CL-based strategies for fairness on expression recognition and Action Unit (AU) detection tasks using popular benchmarks for each; RAF-DB and BP4D. Our experiments show that CL-based methods, on average, outperform popular bias mitigation techniques, strengthening the need for further investigation into CL for the development of fairer FER algorithms.