Mostrar el registro sencillo del ítem

A patch-based architecture for multi-label classification from single label annotations

hal.structure.identifierLaboratoire Bordelais de Recherche en Informatique [LaBRI]
hal.structure.identifierLectra
dc.contributor.authorJOUANNEAU, Warren
hal.structure.identifierLaboratoire Bordelais de Recherche en Informatique [LaBRI]
hal.structure.identifierInstitut universitaire de France [IUF]
dc.contributor.authorBUGEAU, Aurélie
hal.structure.identifierMalt
dc.contributor.authorPALYART, Marc
hal.structure.identifierInstitut de Mathématiques de Bordeaux [IMB]
dc.contributor.authorPAPADAKIS, Nicolas
hal.structure.identifierLectra
dc.contributor.authorVÉZARD, Laurent
dc.date.accessioned2024-04-04T02:40:25Z
dc.date.available2024-04-04T02:40:25Z
dc.date.issued2023
dc.date.conference2023-01-19
dc.identifier.urihttps://oskar-bordeaux.fr/handle/20.500.12278/191064
dc.description.abstractEnIn this paper, we propose a patch-based architecture for multi-label classification problems where only a single positive label is observed in images of the dataset. Our contributions are twofold. First, we introduce a light patch architecture based on the attention mechanism. Next, leveraging on patch embedding self-similarities, we provide a novel strategy for estimating negative examples and deal with positive and unlabeled learning problems. Experiments demonstrate that our architecture can be trained from scratch, whereas pre-training on similar databases is required for related methods from the literature.
dc.language.isoen
dc.title.enA patch-based architecture for multi-label classification from single label annotations
dc.typeCommunication dans un congrès
dc.subject.halInformatique [cs]/Vision par ordinateur et reconnaissance de formes [cs.CV]
dc.identifier.arxiv2209.06530
bordeaux.hal.laboratoriesInstitut de Mathématiques de Bordeaux (IMB) - UMR 5251*
bordeaux.institutionUniversité de Bordeaux
bordeaux.institutionBordeaux INP
bordeaux.institutionCNRS
bordeaux.conference.titleInternational Conference on Computer Vision Theory and Applications (VISAPP'23)
bordeaux.countryPT
bordeaux.conference.cityLisbon
bordeaux.peerReviewedoui
hal.identifierhal-03783915
hal.version1
hal.invitednon
hal.proceedingsoui
hal.conference.end2023-01-21
hal.popularnon
hal.audienceInternationale
hal.origin.linkhttps://hal.archives-ouvertes.fr//hal-03783915v1
bordeaux.COinSctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.date=2023&rft.au=JOUANNEAU,%20Warren&BUGEAU,%20Aur%C3%A9lie&PALYART,%20Marc&PAPADAKIS,%20Nicolas&V%C3%89ZARD,%20Laurent&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