Generalizability and Application of the Skin Reflectance Estimate Based on Dichromatic Separation (SREDS)
This work addresses fairness issues in face recognition for diverse populations, offering a privacy-preserving alternative to race labels, though it is incremental in improving existing skin tone metrics.
The paper tackles the problem of differential performance in face recognition systems across demographics by analyzing the generalizability of the Skin Reflectance Estimate based on Dichromatic Separation (SREDS) as a skin tone metric, finding that SREDS reduces variability within subjects and can substitute for self-reported race labels with minimal performance drop.
Face recognition (FR) systems have become widely used and readily available in recent history. However, differential performance between certain demographics has been identified within popular FR models. Skin tone differences between demographics can be one of the factors contributing to the differential performance observed in face recognition models. Skin tone metrics provide an alternative to self-reported race labels when such labels are lacking or completely not available e.g. large-scale face recognition datasets. In this work, we provide a further analysis of the generalizability of the Skin Reflectance Estimate based on Dichromatic Separation (SREDS) against other skin tone metrics and provide a use case for substituting race labels for SREDS scores in a privacy-preserving learning solution. Our findings suggest that SREDS consistently creates a skin tone metric with lower variability within each subject and SREDS values can be utilized as an alternative to the self-reported race labels at minimal drop in performance. Finally, we provide a publicly available and open-source implementation of SREDS to help the research community. Available at https://github.com/JosephDrahos/SREDS