Investigating Bias and Fairness in Appearance-based Gaze Estimation

ArXi:2604.10707v1 Announce Type: new While appearance-based gaze estimation has achieved significant improvements in accuracy and domain adaptation, the fairness of these systems across different graphic groups remains largely unexplored. To date, there is no comprehensive benchmark quantifying algorithmic bias in gaze estimation. This paper presents the first extensive evaluation of fairness in appearance-based gaze estimation, focusing on ethnicity and gender attributes.