Mitigating Gender Bias in Face Recognition Using the von Mises-Fisher Mixture Model.
Jean-Rémy ContiNathan NoiryVincent DespiegelStéphane GentricStéphan ClémençonPublished in: CoRR (2022)
Keyphrases
- von mises fisher
- mixture model
- unit sphere
- generative model
- gaussian mixture model
- noise model
- em algorithm
- probabilistic model
- model selection
- multi variate
- unsupervised learning
- maximum likelihood
- expectation maximization
- language model
- computer vision
- multivariate data
- noise level
- unsupervised classification
- feature vectors
- face recognition