Algorithmic Discrimination: Formulation and Exploration in Deep Learning-based Face Biometrics
It addresses fairness issues in face biometrics for underrepresented demographic groups, but is incremental as it builds on existing models and databases.
This study investigates algorithmic discrimination in deep learning-based face recognition by analyzing feature spaces and performance across demographic groups, revealing that models trained on popular databases exhibit strong discrimination with large performance differences between groups.
The most popular face recognition benchmarks assume a distribution of subjects without much attention to their demographic attributes. In this work, we perform a comprehensive discrimination-aware experimentation of deep learning-based face recognition. The main aim of this study is focused on a better understanding of the feature space generated by deep models, and the performance achieved over different demographic groups. We also propose a general formulation of algorithmic discrimination with application to face biometrics. The experiments are conducted over the new DiveFace database composed of 24K identities from six different demographic groups. Two popular face recognition models are considered in the experimental framework: ResNet-50 and VGG-Face. We experimentally show that demographic groups highly represented in popular face databases have led to popular pre-trained deep face models presenting strong algorithmic discrimination. That discrimination can be observed both qualitatively at the feature space of the deep models and quantitatively in large performance differences when applying those models in different demographic groups, e.g. for face biometrics.