Show simple item record

Is the U-NET directional-relationship aware?

hal.structure.identifierLaboratoire Traitement et Communication de l'Information [LTCI]
dc.contributor.authorRiva, Mateus
hal.structure.identifierLaboratoire Traitement et Communication de l'Information [LTCI]
dc.contributor.authorGori, Pietro
hal.structure.identifierLaboratoire d'analyse et modélisation de systèmes pour l'aide à la décision [LAMSADE]
dc.contributor.authorYger, Florian
HAL ID: 17768
ORCID: 0000-0002-7182-8062
hal.structure.identifierLIP6
dc.contributor.authorBloch, Isabelle
HAL ID: 175825
ORCID: 0000-0002-6984-1532
dc.date.accessioned2023-01-19T19:15:34Z
dc.date.available2023-01-19T19:15:34Z
dc.date.issued2022-07
dc.identifier.urihttps://basepub.dauphine.psl.eu/handle/123456789/23767
dc.language.isoenen
dc.subjectXAIen
dc.subjectstructural informationen
dc.subjectdirectional relationshipsen
dc.subjectU-Neten
dc.subject.ddc003en
dc.titleIs the U-NET directional-relationship aware?en
dc.typeCommunication / Conférence
dc.description.abstractenCNNs are often assumed to be capable of using contextual information about distinct objects (such as their directional relations) inside their receptive field. However, the nature and limits of this capacity has never been explored in full. We explore a specific type of relationship-directional-using a standard U-Net trained to optimize a cross-entropy loss function for segmentation. We train this network on a pretext segmentation task requiring directional relation reasoning for success and state that, with enough data and a sufficiently large receptive field, it succeeds to learn the proposed task. We further explore what the network has learned by analysing scenarios where the directional relationships are perturbed, and show that the network has learned to reason using these relationships.en
dc.identifier.urlsitehttps://hal.archives-ouvertes.fr/hal-03715361en
dc.subject.ddclabelRecherche opérationnelleen
dc.relation.conftitleIEEE International Conference on Image Processing (ICIP 2022)en
dc.relation.confdate2022-10
dc.relation.confcityBordeauxen
dc.relation.confcountryFranceen
dc.relation.forthcomingnonen
dc.description.ssrncandidatenon
dc.description.halcandidatenonen
dc.description.readershiprechercheen
dc.description.audienceInternationalen
dc.relation.Isversionofjnlpeerreviewedouien
dc.date.updated2023-01-19T19:03:48Z
hal.export.arxivnonen
hal.export.pmcnonen
hal.hide.repecnonen
hal.hide.oainonen
hal.author.functionaut
hal.author.functionaut
hal.author.functionaut
hal.author.functionaut


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record