Self-Supervised Learning in Remote Sensing: A review

Self-Supervised Learning in Remote Sensing: A review

In deep learning research, self-supervised learning (SSL) has received great attention, triggering interest within both the computer vision and remote sensing communities. While there has been big success in computer vision, most of the potential of SSL in the domain of Earth observation remains loc...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE geoscience and remote sensing magazine 2022-12, Vol.10 (4), p.213-247
Hauptverfasser: Wang, Yi, Albrecht, Conrad M., Braham, Nassim Ait Ali, Mou, Lichao, Zhu, Xiao Xiang
Format: Artikel
Sprache:eng
Schlagworte:
Deep learning
Learning systems
Remote sensing
Self-supervised learning
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 247
container_issue 4
container_start_page 213
container_title IEEE geoscience and remote sensing magazine
container_volume 10
creator Wang, Yi
Albrecht, Conrad M.
Braham, Nassim Ait Ali
Mou, Lichao
Zhu, Xiao Xiang
description In deep learning research, self-supervised learning (SSL) has received great attention, triggering interest within both the computer vision and remote sensing communities. While there has been big success in computer vision, most of the potential of SSL in the domain of Earth observation remains locked. In this article, we provide an introduction to and a review of the concepts and latest developments in SSL for computer vision in the context of remote sensing. Further, we provide a preliminary benchmark of modern SSL algorithms on popular remote sensing datasets, verifying the potential of SSL in remote sensing and providing an extended study on data augmentations. Finally, we identify a list of promising directions of future research in SSL for Earth observation (SSL4EO) to pave the way for the fruitful interaction of both domains.
doi_str_mv 10.1109/MGRS.2022.3198244
format Article
fullrecord <record><control><sourceid>crossref_RIE</sourceid><recordid>TN_cdi_ieee_primary_9875399</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9875399</ieee_id><sourcerecordid>10_1109_MGRS_2022_3198244</sourcerecordid><originalsourceid>FETCH-LOGICAL-c2234-9d072932877b61937ffdb9ca7661b5a5120360d491ddddf23427f300bae971fc3</originalsourceid><addsrcrecordid>eNo9j91KAzEQRoMoWGofQLzZF8iaSXaTjHelaCusCF29DvszkZV2WxKt-PamtPjdzPAxZ-AwdgsiBxB4_7Jc17kUUuYK0MqiuGATCdpybRVcpr0wikuF5prNYvwUKbYEBDthRU0bz-vvPYXDEKnPKmrCOIwf2TBma9ruviiraYypecjmWaDDQD837Mo3m0iz85yy96fHt8WKV6_L58W84p2UquDYCyNRSWtMqwGV8b5vsWuM1tCWTQlSKC36AqFP8QmRxish2obQgO_UlMHpbxd2MQbybh-GbRN-HQh3NHdHc3c0d2fzxNydmIGI_u_RmlIhqj91mVLf</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Self-Supervised Learning in Remote Sensing: A review</title><source>IEEE Electronic Library (IEL)</source><creator>Wang, Yi ; Albrecht, Conrad M. ; Braham, Nassim Ait Ali ; Mou, Lichao ; Zhu, Xiao Xiang</creator><creatorcontrib>Wang, Yi ; Albrecht, Conrad M. ; Braham, Nassim Ait Ali ; Mou, Lichao ; Zhu, Xiao Xiang</creatorcontrib><description>In deep learning research, self-supervised learning (SSL) has received great attention, triggering interest within both the computer vision and remote sensing communities. While there has been big success in computer vision, most of the potential of SSL in the domain of Earth observation remains locked. In this article, we provide an introduction to and a review of the concepts and latest developments in SSL for computer vision in the context of remote sensing. Further, we provide a preliminary benchmark of modern SSL algorithms on popular remote sensing datasets, verifying the potential of SSL in remote sensing and providing an extended study on data augmentations. Finally, we identify a list of promising directions of future research in SSL for Earth observation (SSL4EO) to pave the way for the fruitful interaction of both domains.</description><identifier>ISSN: 2473-2397</identifier><identifier>EISSN: 2168-6831</identifier><identifier>DOI: 10.1109/MGRS.2022.3198244</identifier><identifier>CODEN: IGRSCZ</identifier><language>eng</language><publisher>IEEE</publisher><subject>Deep learning ; Learning systems ; Remote sensing ; Self-supervised learning</subject><ispartof>IEEE geoscience and remote sensing magazine, 2022-12, Vol.10 (4), p.213-247</ispartof><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c2234-9d072932877b61937ffdb9ca7661b5a5120360d491ddddf23427f300bae971fc3</citedby><cites>FETCH-LOGICAL-c2234-9d072932877b61937ffdb9ca7661b5a5120360d491ddddf23427f300bae971fc3</cites><orcidid>0000-0002-3096-6610 ; 0000-0001-8407-6413 ; 0000-0001-5530-3613</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/9875399$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,796,27924,27925,54758</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/9875399$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Wang, Yi</creatorcontrib><creatorcontrib>Albrecht, Conrad M.</creatorcontrib><creatorcontrib>Braham, Nassim Ait Ali</creatorcontrib><creatorcontrib>Mou, Lichao</creatorcontrib><creatorcontrib>Zhu, Xiao Xiang</creatorcontrib><title>Self-Supervised Learning in Remote Sensing: A review</title><title>IEEE geoscience and remote sensing magazine</title><addtitle>GRSM</addtitle><description>In deep learning research, self-supervised learning (SSL) has received great attention, triggering interest within both the computer vision and remote sensing communities. While there has been big success in computer vision, most of the potential of SSL in the domain of Earth observation remains locked. In this article, we provide an introduction to and a review of the concepts and latest developments in SSL for computer vision in the context of remote sensing. Further, we provide a preliminary benchmark of modern SSL algorithms on popular remote sensing datasets, verifying the potential of SSL in remote sensing and providing an extended study on data augmentations. Finally, we identify a list of promising directions of future research in SSL for Earth observation (SSL4EO) to pave the way for the fruitful interaction of both domains.</description><subject>Deep learning</subject><subject>Learning systems</subject><subject>Remote sensing</subject><subject>Self-supervised learning</subject><issn>2473-2397</issn><issn>2168-6831</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNo9j91KAzEQRoMoWGofQLzZF8iaSXaTjHelaCusCF29DvszkZV2WxKt-PamtPjdzPAxZ-AwdgsiBxB4_7Jc17kUUuYK0MqiuGATCdpybRVcpr0wikuF5prNYvwUKbYEBDthRU0bz-vvPYXDEKnPKmrCOIwf2TBma9ruviiraYypecjmWaDDQD837Mo3m0iz85yy96fHt8WKV6_L58W84p2UquDYCyNRSWtMqwGV8b5vsWuM1tCWTQlSKC36AqFP8QmRxish2obQgO_UlMHpbxd2MQbybh-GbRN-HQh3NHdHc3c0d2fzxNydmIGI_u_RmlIhqj91mVLf</recordid><startdate>202212</startdate><enddate>202212</enddate><creator>Wang, Yi</creator><creator>Albrecht, Conrad M.</creator><creator>Braham, Nassim Ait Ali</creator><creator>Mou, Lichao</creator><creator>Zhu, Xiao Xiang</creator><general>IEEE</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><orcidid>https://orcid.org/0000-0002-3096-6610</orcidid><orcidid>https://orcid.org/0000-0001-8407-6413</orcidid><orcidid>https://orcid.org/0000-0001-5530-3613</orcidid></search><sort><creationdate>202212</creationdate><title>Self-Supervised Learning in Remote Sensing: A review</title><author>Wang, Yi ; Albrecht, Conrad M. ; Braham, Nassim Ait Ali ; Mou, Lichao ; Zhu, Xiao Xiang</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c2234-9d072932877b61937ffdb9ca7661b5a5120360d491ddddf23427f300bae971fc3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Deep learning</topic><topic>Learning systems</topic><topic>Remote sensing</topic><topic>Self-supervised learning</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Wang, Yi</creatorcontrib><creatorcontrib>Albrecht, Conrad M.</creatorcontrib><creatorcontrib>Braham, Nassim Ait Ali</creatorcontrib><creatorcontrib>Mou, Lichao</creatorcontrib><creatorcontrib>Zhu, Xiao Xiang</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><jtitle>IEEE geoscience and remote sensing magazine</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Wang, Yi</au><au>Albrecht, Conrad M.</au><au>Braham, Nassim Ait Ali</au><au>Mou, Lichao</au><au>Zhu, Xiao Xiang</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Self-Supervised Learning in Remote Sensing: A review</atitle><jtitle>IEEE geoscience and remote sensing magazine</jtitle><stitle>GRSM</stitle><date>2022-12</date><risdate>2022</risdate><volume>10</volume><issue>4</issue><spage>213</spage><epage>247</epage><pages>213-247</pages><issn>2473-2397</issn><eissn>2168-6831</eissn><coden>IGRSCZ</coden><abstract>In deep learning research, self-supervised learning (SSL) has received great attention, triggering interest within both the computer vision and remote sensing communities. While there has been big success in computer vision, most of the potential of SSL in the domain of Earth observation remains locked. In this article, we provide an introduction to and a review of the concepts and latest developments in SSL for computer vision in the context of remote sensing. Further, we provide a preliminary benchmark of modern SSL algorithms on popular remote sensing datasets, verifying the potential of SSL in remote sensing and providing an extended study on data augmentations. Finally, we identify a list of promising directions of future research in SSL for Earth observation (SSL4EO) to pave the way for the fruitful interaction of both domains.</abstract><pub>IEEE</pub><doi>10.1109/MGRS.2022.3198244</doi><tpages>35</tpages><orcidid>https://orcid.org/0000-0002-3096-6610</orcidid><orcidid>https://orcid.org/0000-0001-8407-6413</orcidid><orcidid>https://orcid.org/0000-0001-5530-3613</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier ISSN: 2473-2397
ispartof IEEE geoscience and remote sensing magazine, 2022-12, Vol.10 (4), p.213-247
issn 2473-2397
2168-6831
language eng
recordid cdi_ieee_primary_9875399
source IEEE Electronic Library (IEL)
subjects Deep learning
Learning systems
Remote sensing
Self-supervised learning
title Self-Supervised Learning in Remote Sensing: A review
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-05T03%3A48%3A17IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-crossref_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Self-Supervised%20Learning%20in%20Remote%20Sensing:%20A%20review&rft.jtitle=IEEE%20geoscience%20and%20remote%20sensing%20magazine&rft.au=Wang,%20Yi&rft.date=2022-12&rft.volume=10&rft.issue=4&rft.spage=213&rft.epage=247&rft.pages=213-247&rft.issn=2473-2397&rft.eissn=2168-6831&rft.coden=IGRSCZ&rft_id=info:doi/10.1109/MGRS.2022.3198244&rft_dat=%3Ccrossref_RIE%3E10_1109_MGRS_2022_3198244%3C/crossref_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=9875399&rfr_iscdi=true