Mostrar el registro sencillo del ítem

dc.contributor.authorkang, jian
dc.contributor.authorFernandez-Beltran, Ruben
dc.contributor.authorDuan, Puhong
dc.contributor.authorLiu, Sicong
dc.contributor.authorPlaza, Antonio
dc.date.accessioned2021-01-19T12:13:04Z
dc.date.available2021-01-19T12:13:04Z
dc.date.issued2020-07-14
dc.identifier.citationKANG, Jian, et al. Deep unsupervised embedding for remotely sensed images based on spatially augmented momentum contrast. IEEE Transactions on Geoscience and Remote Sensing, 2020.ca_CA
dc.identifier.urihttp://hdl.handle.net/10234/191293
dc.description.abstractConvolutional neural networks (CNNs) have achieved great success when characterizing remote sensing (RS) images. However, the lack of sufficient annotated data (together with the high complexity of the RS image domain) often makes supervised and transfer learning schemes limited from an operational perspective. Despite the fact that unsupervised methods can potentially relieve these limitations, they are frequently unable to effectively exploit relevant prior knowledge about the RS domain, which may eventually constrain their final performance. In order to address these challenges, this article presents a new unsupervised deep metric learning model, called spatially augmented momentum contrast (SauMoCo), which has been specially designed to characterize unlabeled RS scenes. Based on the first law of geography, the proposed approach defines spatial augmentation criteria to uncover semantic relationships among land cover tiles. Then, a queue of deep embeddings is constructed to enhance the semantic variety of RS tiles within the considered contrastive learning process, where an auxiliary CNN model serves as an updating mechanism. Our experimental comparison, including different state-of-the-art techniques and benchmark RS image archives, reveals that the proposed approach obtains remarkable performance gains when characterizing unlabeled scenes since it is able to substantially enhance the discrimination ability among complex land cover categories. The source codes of this article will be made available to the RS community for reproducible research.ca_CA
dc.format.extent28 p.ca_CA
dc.format.mimetypeapplication/pdfca_CA
dc.language.isoengca_CA
dc.publisherIEEEca_CA
dc.rights.urihttp://rightsstatements.org/vocab/CNE/1.0/*
dc.subjectmeasurementca_CA
dc.subjectsemanticsca_CA
dc.subjectremote sensingca_CA
dc.subjectcomplexity theoryca_CA
dc.subjectfeature extractionca_CA
dc.subjectstandardsca_CA
dc.subjectgeographyca_CA
dc.subjectdeep learning (DL)ca_CA
dc.subjectmetric learningca_CA
dc.subjectremote sensing (RS)ca_CA
dc.subjectscene characterizationca_CA
dc.subjectself-supervised learningca_CA
dc.subjectunsupervised learningca_CA
dc.titleDeep Unsupervised Embedding for Remotely Sensed Images Based on Spatially Augmented Momentum Contrastca_CA
dc.typeinfo:eu-repo/semantics/articleca_CA
dc.identifier.doihttp://dx.doi.org/10.1109/TGRS.2020.3007029
dc.relation.projectIDGrant Number 2018YFB 050500; RTI2018-098651-B-C54; Ref. GR18060; H2020 EOXPOSURE project (No. 734541)ca_CA
dc.rights.accessRightsinfo:eu-repo/semantics/openAccessca_CA
dc.relation.publisherVersionhttps://ieeexplore.ieee.org/document/9140372ca_CA
dc.type.versioninfo:eu-repo/semantics/publishedVersionca_CA


Ficheros en el ítem

Thumbnail

Este ítem aparece en la(s) siguiente(s) colección(ones)

Mostrar el registro sencillo del ítem