Where are my clothes? A multi-level approach for evaluating deep instance segmentation architectures on fashion images
hal.structure.identifier | Lectra | |
hal.structure.identifier | Laboratoire Bordelais de Recherche en Informatique [LaBRI] | |
hal.structure.identifier | Université de Bordeaux [UB] | |
dc.contributor.author | JOUANNEAU, Warren | |
hal.structure.identifier | Laboratoire Bordelais de Recherche en Informatique [LaBRI] | |
dc.contributor.author | BUGEAU, Aurélie | |
hal.structure.identifier | Lectra | |
dc.contributor.author | PALYART, Marc | |
hal.structure.identifier | Institut de Mathématiques de Bordeaux [IMB] | |
dc.contributor.author | PAPADAKIS, Nicolas | |
hal.structure.identifier | Lectra | |
dc.contributor.author | VÉZARD, Laurent | |
dc.date.accessioned | 2024-04-04T02:46:14Z | |
dc.date.available | 2024-04-04T02:46:14Z | |
dc.date.issued | 2021-06-19 | |
dc.date.conference | 2021-06-19 | |
dc.identifier.uri | https://oskar-bordeaux.fr/handle/20.500.12278/191530 | |
dc.description.abstractEn | In this paper we present an extensive evaluation of instance segmentation in the context of images containing clothes. We propose a multi level evaluation that completes the classical overlapping criteria given by IoU. In particular, we quantify both the contour and color content accuracy of the the predicted segmentation masks. We demonstrate that the proposed evaluation framework is relevant to obtain meaningful insights on models performance through experiments conducted on five state of the art instance segmentation methods. | |
dc.language.iso | en | |
dc.source.title | Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops | |
dc.title.en | Where are my clothes? A multi-level approach for evaluating deep instance segmentation architectures on fashion images | |
dc.type | Communication dans un congrès | |
dc.subject.hal | Informatique [cs]/Vision par ordinateur et reconnaissance de formes [cs.CV] | |
bordeaux.page | 3951-3955 | |
bordeaux.hal.laboratories | Institut de Mathématiques de Bordeaux (IMB) - UMR 5251 | * |
bordeaux.institution | Université de Bordeaux | |
bordeaux.institution | Bordeaux INP | |
bordeaux.institution | CNRS | |
bordeaux.conference.title | CVPR Workshop on Computer Vision for Fashion, Art, and Design (CVFAD'21) | |
bordeaux.country | US | |
bordeaux.title.proceeding | Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops | |
bordeaux.conference.city | Virtual event | |
bordeaux.peerReviewed | oui | |
hal.identifier | hal-03272473 | |
hal.version | 1 | |
hal.invited | non | |
hal.proceedings | oui | |
hal.popular | non | |
hal.audience | Internationale | |
hal.origin.link | https://hal.archives-ouvertes.fr//hal-03272473v1 | |
bordeaux.COinS | ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.btitle=Proceedings%20of%20the%20IEEE/CVF%20Conference%20on%20Computer%20Vision%20and%20Pattern%20Recognition%20(CVPR)%20Workshops&rft.date=2021-06-19&rft.spage=3951-3955&rft.epage=3951-3955&rft.au=JOUANNEAU,%20Warren&BUGEAU,%20Aur%C3%A9lie&PALYART,%20Marc&PAPADAKIS,%20Nicolas&V%C3%89ZARD,%20Laurent&rft.genre=unknown |
Fichier(s) constituant ce document
Fichiers | Taille | Format | Vue |
---|---|---|---|
Il n'y a pas de fichiers associés à ce document. |