This title appears in the Scientific Report :
2023
Please use the identifier:
http://dx.doi.org/10.34734/FZJ-2023-02292 in citations.
Please use the identifier: http://dx.doi.org/10.1109/LGRS.2023.3274493 in citations.
Generating Views Using Atmospheric Correction for Contrastive Self-Supervised Learning of Multispectral Images
Generating Views Using Atmospheric Correction for Contrastive Self-Supervised Learning of Multispectral Images
In 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 transf...
Saved in:
Personal Name(s): | Patnala, Ankit (Corresponding author) |
---|---|
Stadtler, Scarlet / Schultz, Martin G. / Gall, Juergen | |
Contributing Institute: |
Jülich Supercomputing Center; JSC |
Published in: | IEEE geoscience and remote sensing letters, 20 (2023) 2502305, S. 1 - 5 |
Imprint: |
New York, NY
IEEE
2023
|
DOI: |
10.34734/FZJ-2023-02292 |
DOI: |
10.1109/LGRS.2023.3274493 |
Document Type: |
Journal Article |
Research Program: |
AI Strategy for Earth system data Earth System Data Exploration Deep Learning for Air Quality and Climate Forecasts Domain-Specific Simulation & Data Life Cycle Labs (SDLs) and Research Groups |
Link: |
Get full text OpenAccess |
Publikationsportal JuSER |
Please use the identifier: http://dx.doi.org/10.1109/LGRS.2023.3274493 in citations.
LEADER | 05484nam a2200757 a 4500 | ||
---|---|---|---|
001 | 1008330 | ||
005 | 20231027114406.0 | ||
024 | 7 | |a 10.1109/LGRS.2023.3274493 |2 doi | |
024 | 7 | |a 1545-598X |2 ISSN | |
024 | 7 | |a 1558-0571 |2 ISSN | |
024 | 7 | |a 10.34734/FZJ-2023-02292 |2 datacite_doi | |
024 | 7 | |a WOS:000995888700003 |2 WOS | |
037 | |a FZJ-2023-02292 | ||
041 | |a English | ||
082 | |a 550 | ||
100 | 1 | |a Patnala, Ankit |0 P:(DE-Juel1)186635 |b 0 |e Corresponding author | |
245 | |a Generating Views Using Atmospheric Correction for Contrastive Self-Supervised Learning of Multispectral Images | ||
260 | |a New York, NY |c 2023 |b IEEE | ||
520 | |a In 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%. | ||
588 | |a Dataset connected to CrossRef, Journals: juser.fz-juelich.de | ||
700 | 1 | |a Stadtler, Scarlet |0 P:(DE-Juel1)180752 |b 1 | |
700 | 1 | |a Schultz, Martin G. |0 P:(DE-Juel1)6952 |b 2 | |
700 | 1 | |a Gall, Juergen |0 0000-0002-9447-3399 |b 3 | |
773 | |a 10.1109/LGRS.2023.3274493 |g Vol. 20, p. 1 - 5 |0 PERI:(DE-600)2138738-2 |n 2502305 |p 1 - 5 |t IEEE geoscience and remote sensing letters |v 20 |y 2023 |x 1545-598X | ||
856 | 4 | |u http://juser.fz-juelich.de/record/1008330/files/Invoice_APC600425249.pdf | |
856 | 4 | |y OpenAccess |u http://juser.fz-juelich.de/record/1008330/files/FZJ-2023-02292_1008330.pdf | |
909 | C | O | |o oai:juser.fz-juelich.de:1008330 |p openaire |p open_access |p OpenAPC |p driver |p VDB |p openCost |p dnbdelivery |
910 | 1 | |a Forschungszentrum Jülich |0 I:(DE-588b)5008462-8 |k FZJ |b 0 |6 P:(DE-Juel1)186635 | |
910 | 1 | |a Forschungszentrum Jülich |0 I:(DE-588b)5008462-8 |k FZJ |b 1 |6 P:(DE-Juel1)180752 | |
910 | 1 | |a Forschungszentrum Jülich |0 I:(DE-588b)5008462-8 |k FZJ |b 2 |6 P:(DE-Juel1)6952 | |
913 | 1 | |a DE-HGF |b Key Technologies |l Engineering Digital Futures – Supercomputing, Data Management and Information Security for Knowledge and Action |1 G:(DE-HGF)POF4-510 |0 G:(DE-HGF)POF4-511 |3 G:(DE-HGF)POF4 |2 G:(DE-HGF)POF4-500 |4 G:(DE-HGF)POF |v Enabling Computational- & Data-Intensive Science and Engineering |9 G:(DE-HGF)POF4-5111 |x 0 | |
914 | 1 | |y 2023 | |
915 | p | c | |a APC keys set |0 PC:(DE-HGF)0000 |2 APC |
915 | |a DBCoverage |0 StatID:(DE-HGF)0160 |2 StatID |b Essential Science Indicators |d 2022-11-17 | ||
915 | |a WoS |0 StatID:(DE-HGF)0113 |2 StatID |b Science Citation Index Expanded |d 2022-11-17 | ||
915 | |a OpenAccess |0 StatID:(DE-HGF)0510 |2 StatID | ||
915 | |a JCR |0 StatID:(DE-HGF)0100 |2 StatID |b IEEE GEOSCI REMOTE S : 2022 |d 2023-10-25 | ||
915 | |a DBCoverage |0 StatID:(DE-HGF)0200 |2 StatID |b SCOPUS |d 2023-10-25 | ||
915 | |a DBCoverage |0 StatID:(DE-HGF)0300 |2 StatID |b Medline |d 2023-10-25 | ||
915 | |a DBCoverage |0 StatID:(DE-HGF)0199 |2 StatID |b Clarivate Analytics Master Journal List |d 2023-10-25 | ||
915 | |a DBCoverage |0 StatID:(DE-HGF)0150 |2 StatID |b Web of Science Core Collection |d 2023-10-25 | ||
915 | |a DBCoverage |0 StatID:(DE-HGF)1160 |2 StatID |b Current Contents - Engineering, Computing and Technology |d 2023-10-25 | ||
915 | |a IF < 5 |0 StatID:(DE-HGF)9900 |2 StatID |d 2023-10-25 | ||
980 | |a journal | ||
980 | |a VDB | ||
980 | |a UNRESTRICTED | ||
980 | |a I:(DE-Juel1)JSC-20090406 | ||
980 | |a APC | ||
980 | 1 | |a APC | |
980 | 1 | |a FullTexts | |
536 | |a AI Strategy for Earth system data |0 G:(DE-Juel1)kiste_20200501 |c kiste_20200501 |f AI Strategy for Earth system data |x 3 | ||
536 | |a Earth System Data Exploration |0 G:(DE-Juel-1)ESDE |c ESDE |x 2 | ||
536 | |a Deep Learning for Air Quality and Climate Forecasts |0 G:(DE-Juel1)deepacf_20191101 |c deepacf_20191101 |f Deep Learning for Air Quality and Climate Forecasts |x 1 | ||
536 | |a Domain-Specific Simulation & Data Life Cycle Labs (SDLs) and Research Groups |0 G:(DE-HGF)POF4-5111 |c POF4-511 |f POF IV |x 0 | ||
336 | |a ARTICLE |2 BibTeX | ||
336 | |a Journal Article |b journal |m journal |0 PUB:(DE-HGF)16 |s 1689675119_6103 |2 PUB:(DE-HGF) | ||
336 | |a Output Types/Journal article |2 DataCite | ||
336 | |a article |2 DRIVER | ||
336 | |a Nanopartikel unedler Metalle (Mg0, Al0, Gd0, Sm0) |0 0 |2 EndNote | ||
336 | |a JOURNAL_ARTICLE |2 ORCID | ||
920 | |l no | ||
920 | |k Jülich Supercomputing Center; JSC |0 I:(DE-Juel1)JSC-20090406 |l Jülich Supercomputing Center |x 0 | ||
990 | |a Patnala, Ankit |0 P:(DE-Juel1)186635 |b 0 |e Corresponding author | ||
991 | |a Gall, Juergen |0 0000-0002-9447-3399 |b 3 | ||
991 | |a Schultz, Martin |0 P:(DE-Juel1)6952 |b 2 | ||
991 | |a Stadtler, Scarlet |0 P:(DE-Juel1)180752 |b 1 |