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

Autor: Conti, Jean-Rémy, Noiry, Nathan, Despiegel, Vincent, Gentric, Stéphane, Clémençon, Stéphan

Publikováno v: Proceedings of the 39th International Conference on Machine Learning, PMLR 162:4344-4369, 2022

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 (

Externí odkaz: http://arxiv.org/abs/2210.13664

Robustness of Facial Recognition to GAN-based Face-morphing Attacks

Autor: Marriott, Richard T., Romdhani, Sami, Gentric, Stéphane, Chen, Liming

Face-morphing attacks have been a cause for concern for a number of years. Striving to remain one step ahead of attackers, researchers have proposed many methods of both creating and detecting morphed images. These detection methods, however, have ge

Externí odkaz: http://arxiv.org/abs/2012.10548

von Mises-Fisher Mixture Model-based Deep learning: Application to Face Verification

Autor: Hasnat, Md. Abul, Bohné, Julien, Milgram, Jonathan, Gentric, Stéphane, Chen, Liming

A number of pattern recognition tasks, \textit{e.g.}, face verification, can be boiled down to classification or clustering of unit length directional feature vectors whose distance can be simply computed by their angle. In this paper, we propose the

Externí odkaz: http://arxiv.org/abs/1706.04264

Learning local metrics from pairwise similarity data

Autor: Bohné, Julien, Ying, Yiming, Gentric, Stéphane, Pontil, Massimiliano

Publikováno v: In Pattern Recognition March 2018 75:315-326

3D head model fitting evaluation protocol on synthetic databases for acquisition system comparison

Autor: Herold, Catherine, Despiegel, Vincent, Gentric, Stéphane, Dubuisson, Séverine, Bloch, Isabelle

Publikováno v: VISAPP 2014-International Conference on Computer Vision Theory and Applications
VISAPP 2014-International Conference on Computer Vision Theory and Applications, 2014, Lisbon, Portugal. pp.296-305

International audience; Automatic face recognition has been integrated in many systems thanks to the improvement of face comparisonalgorithms. One of the main applications using facial biometry is the identity authentication at border control,which h

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::0c07846a0cfc5022d40d061e1ff4b9de
https://hal.telecom-paris.fr/hal-02286829