Fairer Analysis and Demographically Balanced Face Generation for Fairer Face Verification
This work addresses fairness problems in face verification for sensitive demographic groups, representing an incremental improvement over existing methods.
The paper tackled fairness issues in face verification by introducing a controlled generation pipeline that improves fairness more than other bias mitigation approaches, while slightly improving raw performance.
Face recognition and verification are two computer vision tasks whose performances have advanced with the introduction of deep representations. However, ethical, legal, and technical challenges due to the sensitive nature of face data and biases in real-world training datasets hinder their development. Generative AI addresses privacy by creating fictitious identities, but fairness problems remain. Using the existing DCFace SOTA framework, we introduce a new controlled generation pipeline that improves fairness. Through classical fairness metrics and a proposed in-depth statistical analysis based on logit models and ANOVA, we show that our generation pipeline improves fairness more than other bias mitigation approaches while slightly improving raw performance.