001008330 001__ 1008330
001008330 005__ 20231027114406.0
001008330 0247_ $$2doi$$a10.1109/LGRS.2023.3274493
001008330 0247_ $$2ISSN$$a1545-598X
001008330 0247_ $$2ISSN$$a1558-0571
001008330 0247_ $$2datacite_doi$$a10.34734/FZJ-2023-02292
001008330 0247_ $$2WOS$$aWOS:000995888700003
001008330 037__ $$aFZJ-2023-02292
001008330 041__ $$aEnglish
001008330 082__ $$a550
001008330 1001_ $$0P:(DE-Juel1)186635$$aPatnala, Ankit$$b0$$eCorresponding author
001008330 245__ $$aGenerating Views Using Atmospheric Correction for Contrastive Self-Supervised Learning of Multispectral Images
001008330 260__ $$aNew York, NY$$bIEEE$$c2023
001008330 3367_ $$2DRIVER$$aarticle
001008330 3367_ $$2DataCite$$aOutput Types/Journal article
001008330 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1689675119_6103
001008330 3367_ $$2BibTeX$$aARTICLE
001008330 3367_ $$2ORCID$$aJOURNAL_ARTICLE
001008330 3367_ $$00$$2EndNote$$aJournal Article
001008330 520__ $$aIn remote sensing, plenty of multispectral images are publicly available from various landcover satellite missions. Contrastive self-supervised learning is commonly applied to unlabeled data but relies on domain-specific transformations used for learning. When focusing on vegetation, standard transformations from image processing cannot be applied to the near-infrared (NIR) channel, which carries valuable information about the vegetation state. Therefore, we use contrastive learning, relying on different views of unlabeled, multispectral images to obtain a pretrained model to improve the accuracy scores on small-sized remote sensing datasets. This study presents the generation of additional views tailored to remote sensing images using atmospheric correction as an alternative transformation to color jittering. The purpose of the atmospheric transformation is to provide a physically consistent transformation. The proposed transformation can be easily integrated with multiple channels to exploit spectral signatures of objects. Our approach can be applied to other remote sensing tasks. Using this transformation leads to improved classification accuracy of up to 6%.
001008330 536__ $$0G:(DE-HGF)POF4-5111$$a5111 - Domain-Specific Simulation & Data Life Cycle Labs (SDLs) and Research Groups (POF4-511)$$cPOF4-511$$fPOF IV$$x0
001008330 536__ $$0G:(DE-Juel1)deepacf_20191101$$aDeep Learning for Air Quality and Climate Forecasts (deepacf_20191101)$$cdeepacf_20191101$$fDeep Learning for Air Quality and Climate Forecasts$$x1
001008330 536__ $$0G:(DE-Juel-1)ESDE$$aEarth System Data Exploration (ESDE)$$cESDE$$x2
001008330 536__ $$0G:(DE-Juel1)kiste_20200501$$aAI Strategy for Earth system data (kiste_20200501)$$ckiste_20200501$$fAI Strategy for Earth system data$$x3
001008330 588__ $$aDataset connected to CrossRef, Journals: juser.fz-juelich.de
001008330 7001_ $$0P:(DE-Juel1)180752$$aStadtler, Scarlet$$b1
001008330 7001_ $$0P:(DE-Juel1)6952$$aSchultz, Martin G.$$b2
001008330 7001_ $$00000-0002-9447-3399$$aGall, Juergen$$b3
001008330 773__ $$0PERI:(DE-600)2138738-2$$a10.1109/LGRS.2023.3274493$$gVol. 20, p. 1 - 5$$n2502305$$p1 - 5$$tIEEE geoscience and remote sensing letters$$v20$$x1545-598X$$y2023
001008330 8564_ $$uhttps://juser.fz-juelich.de/record/1008330/files/Invoice_APC600425249.pdf
001008330 8564_ $$uhttps://juser.fz-juelich.de/record/1008330/files/FZJ-2023-02292_1008330.pdf$$yOpenAccess
001008330 8767_ $$8APC600425249$$92023-06-13$$a1200193992$$d2023-06-19$$ePage charges$$jZahlung erfolgt$$zUSD 460,-
001008330 909CO $$ooai:juser.fz-juelich.de:1008330$$pdnbdelivery$$popenCost$$pVDB$$pdriver$$pOpenAPC$$popen_access$$popenaire
001008330 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)186635$$aForschungszentrum Jülich$$b0$$kFZJ
001008330 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)180752$$aForschungszentrum Jülich$$b1$$kFZJ
001008330 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)6952$$aForschungszentrum Jülich$$b2$$kFZJ
001008330 9131_ $$0G:(DE-HGF)POF4-511$$1G:(DE-HGF)POF4-510$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5111$$aDE-HGF$$bKey Technologies$$lEngineering Digital Futures – Supercomputing, Data Management and Information Security for Knowledge and Action$$vEnabling Computational- & Data-Intensive Science and Engineering$$x0
001008330 9141_ $$y2023
001008330 915pc $$0PC:(DE-HGF)0000$$2APC$$aAPC keys set
001008330 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2022-11-17
001008330 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2022-11-17
001008330 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
001008330 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bIEEE GEOSCI REMOTE S : 2022$$d2023-10-25
001008330 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2023-10-25
001008330 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2023-10-25
001008330 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2023-10-25
001008330 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2023-10-25
001008330 915__ $$0StatID:(DE-HGF)1160$$2StatID$$aDBCoverage$$bCurrent Contents - Engineering, Computing and Technology$$d2023-10-25
001008330 915__ $$0StatID:(DE-HGF)9900$$2StatID$$aIF < 5$$d2023-10-25
001008330 920__ $$lno
001008330 9201_ $$0I:(DE-Juel1)JSC-20090406$$kJSC$$lJülich Supercomputing Center$$x0
001008330 980__ $$ajournal
001008330 980__ $$aVDB
001008330 980__ $$aUNRESTRICTED
001008330 980__ $$aI:(DE-Juel1)JSC-20090406
001008330 980__ $$aAPC
001008330 9801_ $$aAPC
001008330 9801_ $$aFullTexts