Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Feutry, Clément"'
Publikováno v:
World Conference on Explainable Artificial Intelligence, 2024
Recent research in explainability has given rise to numerous post-hoc attribution methods aimed at enhancing our comprehension of the outputs of black-box machine learning models. However, evaluating the quality of explanations lacks a cohesive appro
Externí odkaz:
http://arxiv.org/abs/2407.19897
Statistical methods protecting sensitive information or the identity of the data owner have become critical to ensure privacy of individuals as well as of organizations. This paper investigates anonymization methods based on representation learning a
Externí odkaz:
http://arxiv.org/abs/1802.09386
Autor:
Feutry, Clément
Publikováno v:
Image Processing [eess.IV]. Université Paris Saclay (COmUE), 2019. English. ⟨NNT : 2019SACLS479⟩
The work presented here is for a first part at the cross section of deep learning and anonymization. A full framework was developed in order to identify and remove to a certain extant, in an automated manner, the features linked to an identity in the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______2592::8965f8743e4d1516c4fc1110fb5d72e7
https://tel.archives-ouvertes.fr/tel-03132304
https://tel.archives-ouvertes.fr/tel-03132304
Publikováno v:
XXVIIème Colloque francophone de traitement du signal et des images (Gretsi 2019)
XXVIIème Colloque francophone de traitement du signal et des images (Gretsi 2019), Aug 2019, Lille, France
XXVIIème Colloque francophone de traitement du signal et des images (Gretsi 2019), Aug 2019, Lille, France
International audience; L'utilisation croissante de réseaux de neurones dans le traitement automatique de données soulève de nouvelles problématiques. L'une d'elles est la détection de décalage des covariables d'entrées. Ce décalage entraîne
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::ab8fbc37b4123631560e978947429bd3
https://hal-centralesupelec.archives-ouvertes.fr/hal-02172298/file/GRETSI_2019.pdf
https://hal-centralesupelec.archives-ouvertes.fr/hal-02172298/file/GRETSI_2019.pdf
Autor:
Feutry, Clément
Publikováno v:
Image Processing [eess.IV]. Université Paris Saclay (COmUE), 2019. English. ⟨NNT : 2019SACLS479⟩
The work presented here is for a first part at the cross section of deep learning and anonymization. A full framework was developed in order to identify and remove to a certain extant, in an automated manner, the features linked to an identity in the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::8965f8743e4d1516c4fc1110fb5d72e7
https://theses.hal.science/tel-03132304
https://theses.hal.science/tel-03132304