Mostrar el registro sencillo del ítem
Multi-task deep learning for image segmentation using recursive approximation tasks
hal.structure.identifier | Department of Applied Mathematics and Theoretical Physics [DAMTP] | |
dc.contributor.author | KE, Rihuan | |
hal.structure.identifier | Laboratoire Bordelais de Recherche en Informatique [LaBRI] | |
dc.contributor.author | BUGEAU, Aurélie | |
hal.structure.identifier | Institut de Mathématiques de Bordeaux [IMB] | |
dc.contributor.author | PAPADAKIS, Nicolas | |
dc.contributor.author | KIRKLAND, Mark | |
dc.contributor.author | SCHUETZ, Peter | |
hal.structure.identifier | Department of Applied Mathematics and Theoretical Physics [DAMTP] | |
dc.contributor.author | SCHÖNLIEB, Carola-Bibiane | |
dc.date.accessioned | 2024-04-04T02:54:29Z | |
dc.date.available | 2024-04-04T02:54:29Z | |
dc.date.issued | 2021 | |
dc.identifier.issn | 1057-7149 | |
dc.identifier.uri | https://oskar-bordeaux.fr/handle/20.500.12278/192276 | |
dc.description.abstractEn | Fully supervised deep neural networks for segmentation usually require a massive amount of pixel-level labels which are manually expensive to create. In this work, we develop a multi-task learning method to relax this constraint. We regard the segmentation problem as a sequence of approximation subproblems that are recursively defined and in increasing levels of approximation accuracy. The subproblems are handled by a framework that consists of 1) a segmentation task that learns from pixel-level ground truth segmentation masks of a small fraction of the images, 2) a recursive approximation task that conducts partial object regions learning and data-driven mask evolution starting from partial masks of each object instance, and 3) other problem oriented auxiliary tasks that are trained with sparse annotations and promote the learning of dedicated features. Most training images are only labeled by (rough) partial masks, which do not contain exact object boundaries, rather than by their full segmentation masks. During the training phase, the approximation task learns the statistics of these partial masks, and the partial regions are recursively increased towards object boundaries aided by the learned information from the segmentation task in a fully data-driven fashion. The network is trained on an extremely small amount of precisely segmented images and a large set of coarse labels. Annotations can thus be obtained in a cheap way. We demonstrate the efficiency of our approach in three applications with microscopy images and ultrasound images. | |
dc.language.iso | en | |
dc.publisher | Institute of Electrical and Electronics Engineers | |
dc.title.en | Multi-task deep learning for image segmentation using recursive approximation tasks | |
dc.type | Article de revue | |
dc.identifier.doi | 10.1109/TIP.2021.3062726 | |
dc.subject.hal | Informatique [cs]/Traitement du signal et de l'image | |
dc.identifier.arxiv | 2005.13053 | |
dc.description.sponsorshipEurope | Nonlocal Methods for Arbitrary Data Sources | |
bordeaux.journal | IEEE Transactions on Image Processing | |
bordeaux.page | 3555-3567 | |
bordeaux.volume | 30 | |
bordeaux.hal.laboratories | Institut de Mathématiques de Bordeaux (IMB) - UMR 5251 | * |
bordeaux.institution | Université de Bordeaux | |
bordeaux.institution | Bordeaux INP | |
bordeaux.institution | CNRS | |
bordeaux.peerReviewed | oui | |
hal.identifier | hal-02638394 | |
hal.version | 1 | |
hal.popular | non | |
hal.audience | Internationale | |
hal.origin.link | https://hal.archives-ouvertes.fr//hal-02638394v1 | |
bordeaux.COinS | ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.jtitle=IEEE%20Transactions%20on%20Image%20Processing&rft.date=2021&rft.volume=30&rft.spage=3555-3567&rft.epage=3555-3567&rft.eissn=1057-7149&rft.issn=1057-7149&rft.au=KE,%20Rihuan&BUGEAU,%20Aur%C3%A9lie&PAPADAKIS,%20Nicolas&KIRKLAND,%20Mark&SCHUETZ,%20Peter&rft.genre=article |
Archivos en el ítem
Archivos | Tamaño | Formato | Ver |
---|---|---|---|
No hay archivos asociados a este ítem. |