Mitigating Gender Bias in Face Recognition Using the von Mises-Fisher Mixture Model

arXiv:2210.13664v2 Announce Type: replace
Abstract: In spite of the high performance and reliability of deep learning algorithms in a wide range of everyday applications, many investigations tend to show that a lot of models exhibit biases, discriminating against specific subgroups of the population (e.g. gender, ethnicity). This urges the practitioner to develop fair systems with a uniform/comparable performance across sensitive groups. In this work, we investigate the gender bias of deep Face Recognition networks. In order to measure this bias, …

abstract algorithms applications arxiv bias biases cs.ai cs.cv deep learning deep learning algorithms face face recognition fisher gender gender bias investigations performance population recognition reliability show subgroups type