Vis enkel innførsel

dc.contributor.authorLuppino, Luigi Tommaso
dc.contributor.authorKampffmeyer, Michael
dc.contributor.authorBianchi, Filippo Maria
dc.contributor.authorMoser, Gabriele
dc.contributor.authorSerpico, Sebastiano Bruno
dc.contributor.authorJenssen, Robert
dc.contributor.authorAnfinsen, Stian Normann
dc.date.accessioned2021-06-22T07:48:21Z
dc.date.available2021-06-22T07:48:21Z
dc.date.issued2021-02-17
dc.description.abstractImage translation with convolutional neural networks has recently been used as an approach to multimodal change detection. Existing approaches train the networks by exploiting supervised information of the change areas, which, however, is not always available. A main challenge in the unsupervised problem setting is to avoid that change pixels affect the learning of the translation function. We propose two new network architectures trained with loss functions weighted by priors that reduce the impact of change pixels on the learning objective. The change prior is derived in an unsupervised fashion from relational pixel information captured by domain-specific affinity matrices. Specifically, we use the vertex degrees associated with an absolute affinity difference matrix and demonstrate their utility in combination with cycle consistency and adversarial training. The proposed neural networks are compared with the state-of-the-art algorithms. Experiments conducted on three real data sets show the effectiveness of our methodology.en_US
dc.description© 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.en_US
dc.identifier.citationLuppino, Kampffmeyer, Bianchi, Moser, Serpico, Jenssen, Anfinsen. Deep Image Translation With an Affinity-Based Change Prior for Unsupervised Multimodal Change Detection. IEEE Transactions on Geoscience and Remote Sensing. 2021en_US
dc.identifier.cristinIDFRIDAID 1896322
dc.identifier.doi10.1109/TGRS.2021.3056196
dc.identifier.issn0196-2892
dc.identifier.issn1558-0644
dc.identifier.urihttps://hdl.handle.net/10037/21506
dc.language.isoengen_US
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)en_US
dc.relation.journalIEEE Transactions on Geoscience and Remote Sensing
dc.relation.projectIDinfo:eu-repo/grantAgreement/RCN/ROMFORSK/251327/Norway/Change detection in heterogeneous remote sensing images//en_US
dc.rights.accessRightsopenAccessen_US
dc.rights.holder© Copyright 2021 IEEE - All rights reserved.en_US
dc.subjectVDP::Technology: 500en_US
dc.subjectVDP::Teknologi: 500en_US
dc.subjectVDP::Mathematics and natural science: 400en_US
dc.subjectVDP::Matematikk og Naturvitenskap: 400en_US
dc.titleDeep Image Translation With an Affinity-Based Change Prior for Unsupervised Multimodal Change Detectionen_US
dc.type.versionacceptedVersionen_US
dc.typeJournal articleen_US
dc.typeTidsskriftartikkelen_US
dc.typePeer revieweden_US


Tilhørende fil(er)

Thumbnail

Denne innførselen finnes i følgende samling(er)

Vis enkel innførsel