Mostrar el registro sencillo del ítem

POPCORN: Progressive Pseudo-labeling with Consistency Regularization and Neighboring

hal.structure.identifierLaboratoire Bordelais de Recherche en Informatique [LaBRI]
dc.contributor.authorKAMRAOUI, Reda Abdellah
hal.structure.identifierLaboratoire Bordelais de Recherche en Informatique [LaBRI]
dc.contributor.authorTA, Vinh-Thong
hal.structure.identifierInstitut de Mathématiques de Bordeaux [IMB]
dc.contributor.authorPAPADAKIS, Nicolas
dc.contributor.authorCOMPAIRE, Fanny
hal.structure.identifierITACA
dc.contributor.authorMANJON, José V
hal.structure.identifierLaboratoire Bordelais de Recherche en Informatique [LaBRI]
dc.contributor.authorCOUPÉ, Pierrick
dc.date2021
dc.date.accessioned2024-04-04T02:45:07Z
dc.date.available2024-04-04T02:45:07Z
dc.date.issued2021
dc.date.conference2021-09-27
dc.identifier.urihttps://oskar-bordeaux.fr/handle/20.500.12278/191439
dc.description.abstractEnSemi-supervised learning (SSL) uses unlabeled data to compensate for the scarcity of annotated images and the lack of method generalization to unseen domains, two usual problems in medical segmentation tasks. In this work, we propose POPCORN, a novel method combining consistency regularization and pseudo-labeling designed for image segmentation. The proposed framework uses high-level regularization to constrain our segmentation model to use similar latent features for images with similar segmentations. POPCORN estimates a proximity graph to select data from easiest ones to more difficult ones, in order to ensure accurate pseudo-labeling and to limit confirmation bias. Applied to multiple sclerosis lesion segmentation, our method demonstrates competitive results compared to other state-of-the-art SSL strategies.
dc.description.sponsorshipApprentissage profond pour la volumétrie cérébrale : vers le BigData en neuroscience - ANR-18-CE45-0013
dc.language.isoen
dc.subject.enMS lesion segmentation
dc.subject.enConsistency regularization
dc.subject.enPseudo-labeling
dc.subject.enSemi-supervised Learning
dc.title.enPOPCORN: Progressive Pseudo-labeling with Consistency Regularization and Neighboring
dc.typeCommunication dans un congrès
dc.identifier.doi10.1007/978-3-030-87196-3_35
dc.subject.halInformatique [cs]/Traitement du signal et de l'image
dc.identifier.arxiv2109.06361
bordeaux.page373-382
bordeaux.volume12902
bordeaux.hal.laboratoriesInstitut de Mathématiques de Bordeaux (IMB) - UMR 5251*
bordeaux.institutionUniversité de Bordeaux
bordeaux.institutionBordeaux INP
bordeaux.institutionCNRS
bordeaux.conference.titleInternational Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI'21)
bordeaux.countryFR
bordeaux.conference.cityStrasbourg (virtual)
bordeaux.peerReviewedoui
hal.identifierhal-03365185
hal.version1
hal.invitednon
hal.proceedingsoui
hal.popularnon
hal.audienceInternationale
hal.origin.linkhttps://hal.archives-ouvertes.fr//hal-03365185v1
bordeaux.COinSctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.date=2021&rft.volume=12902&rft.spage=373-382&rft.epage=373-382&rft.au=KAMRAOUI,%20Reda%20Abdellah&TA,%20Vinh-Thong&PAPADAKIS,%20Nicolas&COMPAIRE,%20Fanny&MANJON,%20Jos%C3%A9%20V&rft.genre=unknown


Archivos en el ítem

ArchivosTamañoFormatoVer

No hay archivos asociados a este ítem.

Este ítem aparece en la(s) siguiente(s) colección(ones)

Mostrar el registro sencillo del ítem