Dual Consistency Alignment Based Self-Supervised Learning for SAR Target Recognition With Speckle Noise Resistance
Deep-learning-based on convolutional neural networks (CNN) has been widely applied in synthetic aperture radar (SAR) target recognition and made significant progress. However, due to the physical effects of the equipment used to collect images, various degrees of speckle noise will be introduced int...
Saved in:
Published in | IEEE journal of selected topics in applied earth observations and remote sensing Vol. 16; pp. 3915 - 3928 |
---|---|
Main Authors | , , , , , , , , |
Format | Journal Article |
Language | English |
Published |
Piscataway
IEEE
2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Deep-learning-based on convolutional neural networks (CNN) has been widely applied in synthetic aperture radar (SAR) target recognition and made significant progress. However, due to the physical effects of the equipment used to collect images, various degrees of speckle noise will be introduced into SAR images. Traditional CNN-based SAR target recognition methods are premised on the same noise intensity in the training and testing set, which is contrary to the target recognition in practice. To alleviate this problem, we propose a novel speckle noise resistant framework for SAR target recognition, called dual-consistency-alignment-based self-supervised learning. First, original SAR images are randomly added to speckle noise with different thresholds through multiplicative noise, after which contrastive pretraining is performed on unlabeled data. During this period, we combine instance pseudolabel consistency alignment and feature consistency alignment to align multiple threshold speckle noise views with original views under the same targets. Finally, the pretrained model is migrated to the downstream SAR speckle noise target recognition task. In this article, speckle noise modeling is conducted based on moving and stationary target capture and recognition data testing set, and experiment results reveal that this method can adapt to different intensities of speckle noise, is robust to modeled SAR image recognition, and maintains a high recognition rate even in small-sample learning. |
---|---|
AbstractList | Deep-learning-based on convolutional neural networks (CNN) has been widely applied in synthetic aperture radar (SAR) target recognition and made significant progress. However, due to the physical effects of the equipment used to collect images, various degrees of speckle noise will be introduced into SAR images. Traditional CNN-based SAR target recognition methods are premised on the same noise intensity in the training and testing set, which is contrary to the target recognition in practice. To alleviate this problem, we propose a novel speckle noise resistant framework for SAR target recognition, called dual-consistency-alignment-based self-supervised learning. First, original SAR images are randomly added to speckle noise with different thresholds through multiplicative noise, after which contrastive pretraining is performed on unlabeled data. During this period, we combine instance pseudolabel consistency alignment and feature consistency alignment to align multiple threshold speckle noise views with original views under the same targets. Finally, the pretrained model is migrated to the downstream SAR speckle noise target recognition task. In this article, speckle noise modeling is conducted based on moving and stationary target capture and recognition data testing set, and experiment results reveal that this method can adapt to different intensities of speckle noise, is robust to modeled SAR image recognition, and maintains a high recognition rate even in small-sample learning. |
Author | Jiang, Ziyi Liao, Jinrui Piuri, Vincenzo Genovese, Angelo Wang, Wenqi Ying, Zilu Zhai, Yikui Sun, Bing Scotti, Fabio |
Author_xml | – sequence: 1 givenname: Yikui orcidid: 0000-0003-0154-9743 surname: Zhai fullname: Zhai, Yikui email: yikuizhai@163.com organization: Department of Intelligent Manufacturing, Wuyi University, Jiangmen, China – sequence: 2 givenname: Jinrui orcidid: 0000-0002-2093-7701 surname: Liao fullname: Liao, Jinrui email: jinrui_liao@163.com organization: Department of Intelligent Manufacturing, Wuyi University, Jiangmen, China – sequence: 3 givenname: Bing orcidid: 0000-0002-5520-2406 surname: Sun fullname: Sun, Bing email: bingsun@buaa.edu.cn organization: School of Electronics and Information Engineering, Beihang University, Beijing, China – sequence: 4 givenname: Ziyi orcidid: 0000-0001-6621-7753 surname: Jiang fullname: Jiang, Ziyi email: zylofor@foxmail.com organization: Department of Intelligent Manufacturing, Wuyi University, Jiangmen, China – sequence: 5 givenname: Zilu orcidid: 0000-0002-3074-5586 surname: Ying fullname: Ying, Zilu email: ziluy@163.com organization: Department of Intelligent Manufacturing, Wuyi University, Jiangmen, China – sequence: 6 givenname: Wenqi orcidid: 0000-0002-1185-4867 surname: Wang fullname: Wang, Wenqi email: wenqiwang27@163.com organization: Department of Intelligent Manufacturing, Wuyi University, Jiangmen, China – sequence: 7 givenname: Angelo orcidid: 0000-0002-3683-4723 surname: Genovese fullname: Genovese, Angelo email: angelo.genovese@unimi.it organization: Department of Computer Science and Dipartimento di Informatica, Università Degli Studi di Milano, Milano, Italy – sequence: 8 givenname: Vincenzo orcidid: 0000-0003-3178-8198 surname: Piuri fullname: Piuri, Vincenzo email: vincenzo.piuri@unimi.it organization: Department of Computer Science and Dipartimento di Informatica, Università Degli Studi di Milano, Milano, Italy – sequence: 9 givenname: Fabio orcidid: 0000-0002-4277-3701 surname: Scotti fullname: Scotti, Fabio email: fabio.scotti@unimi.it organization: Department of Computer Science and Dipartimento di Informatica, Università Degli Studi di Milano, Milano, Italy |
BookMark | eNpNUUtvEzEQtlArkRZ-ARwscd7Ub6-PIUBbFFEpG8TRcrzjxWFrB-8Gqf--G7ZCnEYz8z1m9F2hi5QTIPSOkiWlxNx8bXarbbNkhPElZ0rXTLxCC0Ylrajk8gItqOGmooKI1-hqGA6EKKYNX6Dy6eR6vM5piMMIyT_hVR-79AhpxB_dAC1uoA9VczpC-RPP_QZcSTF1OOSCm9UW71zpYMRb8LlLcYw54R9x_ImbI_hfPeBveeJN67ODSx7eoMvg-gHevtRr9P3L5936rto83N6vV5vKC2LGSjIDArQI3gWjPN8H0CGYwGSoKQtMayMClXqvpHZuekZyYFTUitd7alTNr9H9rNtmd7DHEh9debLZRft3kEtnXRmj78GqVtSh3RtBPRHOCUOVpzJopVoCgdBJ68OsdSz59wmG0R7yqaTpfMtqUtdcTr4Tis8oX_IwFAj_XCmx56DsHJQ9B2VfgppY72dWBID_GJRwqRV_BuFqkSE |
CODEN | IJSTHZ |
CitedBy_id | crossref_primary_10_1016_j_jag_2024_103662 |
Cites_doi | 10.1109/TGRS.2017.2776357 10.1109/TGRS.2021.3057768 10.1109/ICCV.2017.74 10.1109/JSTARS.2020.3044643 10.1016/j.patcog.2020.107787 10.1109/JSTARS.2020.3036602 10.1109/CVPR52688.2022.01617 10.1109/JSTARS.2022.3155406 10.1109/JSTARS.2020.3038683 10.1109/TGRS.2021.3076446 10.1007/s41651-019-0042-1 10.1109/JSTARS.2021.3090418 10.1109/LGRS.2018.2877599 10.1109/CVPR46437.2021.01549 10.3390/rs14184632 10.1109/JSTARS.2020.3039235 10.1109/JSTARS.2021.3104267 10.1109/CVPR42600.2020.00674 10.1609/aaai.v36i1.19972 10.1109/JSTARS.2021.3104726 10.1109/IGARSS.2015.7326637 10.1109/JSTARS.2022.3162641 10.1109/IGARSS.2017.8128201 10.1109/LGRS.2018.2865608 10.1109/CVPR42600.2020.00975 10.1109/JSTARS.2021.3059991 10.3390/rs12091385 10.1109/CVPR46437.2021.00113 10.1109/TGRS.2016.2551720 10.1109/JSTARS.2021.3063335 10.1109/JSTARS.2020.2973920 10.1109/TGRS.2022.3192256 10.1109/CVPR52688.2022.00203 10.1109/CVPR.2018.00393 10.1109/JSTARS.2021.3050108 10.1109/LGRS.2021.3132020 10.1007/978-3-319-46487-9_40 10.1109/JSTARS.2021.3056883 10.1109/TGRS.2021.3100137 10.1109/LGRS.2017.2698213 10.1109/IGARSS.2018.8519431 10.1109/CVPR.2006.100 10.1109/TIP.2021.3104179 10.1109/JSTARS.2019.2907655 10.1109/LGRS.2015.2513754 |
ContentType | Journal Article |
Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023 |
Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023 |
DBID | 97E ESBDL RIA RIE AAYXX CITATION 7UA 8FD C1K F1W FR3 H8D H96 KR7 L.G L7M DOA |
DOI | 10.1109/JSTARS.2023.3267824 |
DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005-present IEEE Open Access Journals IEEE All-Society Periodicals Package (ASPP) 1998-Present IEEE Electronic Library Online CrossRef Water Resources Abstracts Technology Research Database Environmental Sciences and Pollution Management ASFA: Aquatic Sciences and Fisheries Abstracts Engineering Research Database Aerospace Database Aquatic Science & Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy & Non-Living Resources Civil Engineering Abstracts Aquatic Science & Fisheries Abstracts (ASFA) Professional Advanced Technologies Database with Aerospace Directory of Open Access Journals |
DatabaseTitle | CrossRef Aerospace Database Civil Engineering Abstracts Aquatic Science & Fisheries Abstracts (ASFA) Professional Aquatic Science & Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy & Non-Living Resources Technology Research Database ASFA: Aquatic Sciences and Fisheries Abstracts Engineering Research Database Advanced Technologies Database with Aerospace Water Resources Abstracts Environmental Sciences and Pollution Management |
DatabaseTitleList | Aerospace Database |
Database_xml | – sequence: 1 dbid: DOA name: DOAJ Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: RIE name: IEEE Xplore url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/ sourceTypes: Publisher |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Geology |
EISSN | 2151-1535 |
EndPage | 3928 |
ExternalDocumentID | oai_doaj_org_article_6d48fdb941c04aa4916c15f766d0ef01 10_1109_JSTARS_2023_3267824 10103576 |
Genre | orig-research |
GrantInformation_xml | – fundername: Jiangmen City Basic and Applied Basic Research Foundation grantid: 2021030103230006 670 – fundername: Key Research Projects for Universities of Guangdong Provincial Education Department grantid: 2020ZDZX3031 – fundername: Greater Bay Area International Science and Technology Innovation Cooperation Project grantid: 2021A050530080; 2021A0505060011 – fundername: Basic and Applied Basic Research Foundation of Guangdong Province; Guangdong Basic and Applied Basic Research Foundation grantid: 2019A1515010716; 2021A1515011576; 2017KCXTD015 funderid: 10.13039/501100021171 – fundername: Guangdong, Hong Kong, Macao |
GroupedDBID | 0R~ 29I 4.4 5GY 5VS 6IK 97E AAFWJ AAJGR ABVLG ACIWK AENEX AETIX AFPKN AFRAH ALMA_UNASSIGNED_HOLDINGS BEFXN BFFAM BGNUA BKEBE BPEOZ DU5 EBS EJD ESBDL GROUPED_DOAJ HZ~ IFIPE IPLJI JAVBF M43 O9- OCL OK1 RIA RIE RIG RNS AAYXX CITATION 7UA 8FD C1K F1W FR3 H8D H96 KR7 L.G L7M |
ID | FETCH-LOGICAL-c409t-529e4e74fcaf96c3bfe7ff9f25f812f27794f157b657aa79353e2148638b19683 |
IEDL.DBID | DOA |
ISSN | 1939-1404 |
IngestDate | Thu Sep 05 15:40:21 EDT 2024 Fri Sep 13 00:05:09 EDT 2024 Fri Aug 23 00:40:01 EDT 2024 Wed Jun 26 19:28:43 EDT 2024 |
IsDoiOpenAccess | true |
IsOpenAccess | true |
IsPeerReviewed | true |
IsScholarly | true |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-c409t-529e4e74fcaf96c3bfe7ff9f25f812f27794f157b657aa79353e2148638b19683 |
ORCID | 0000-0003-0154-9743 0000-0002-1185-4867 0000-0003-3178-8198 0000-0002-5520-2406 0000-0002-2093-7701 0000-0002-3683-4723 0000-0001-6621-7753 0000-0002-3074-5586 0000-0002-4277-3701 |
OpenAccessLink | https://doaj.org/article/6d48fdb941c04aa4916c15f766d0ef01 |
PQID | 2808835863 |
PQPubID | 75722 |
PageCount | 14 |
ParticipantIDs | ieee_primary_10103576 proquest_journals_2808835863 doaj_primary_oai_doaj_org_article_6d48fdb941c04aa4916c15f766d0ef01 crossref_primary_10_1109_JSTARS_2023_3267824 |
PublicationCentury | 2000 |
PublicationDate | 20230000 2023-00-00 20230101 2023-01-01 |
PublicationDateYYYYMMDD | 2023-01-01 |
PublicationDate_xml | – year: 2023 text: 20230000 |
PublicationDecade | 2020 |
PublicationPlace | Piscataway |
PublicationPlace_xml | – name: Piscataway |
PublicationTitle | IEEE journal of selected topics in applied earth observations and remote sensing |
PublicationTitleAbbrev | JSTARS |
PublicationYear | 2023 |
Publisher | IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
Publisher_xml | – name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
References | ref13 ref12 ref56 ref15 ref59 ref58 ref53 ref52 ref11 ref55 ref10 goyal (ref48) 2022 ref17 ref16 ref19 gidaris (ref36) 2018 chen (ref39) 2020 ref18 hendrycks (ref24) 2019 noroozi (ref33) 2016 ref51 ref50 wang (ref57) 2022; 19 ref45 ref47 ref41 ref43 ref8 ref7 ref9 ref4 ref3 ref6 ref5 ref40 ref35 ref34 ref37 ref31 ref30 ref32 ref1 ref38 liu (ref2) 2022; 60 ref23 patacchiola (ref26) 2020 ref25 qin (ref14) 2021; 19 ref20 ref22 ref21 ref28 ref27 ref29 grill (ref42) 2020 jiang (ref46) 2021 van der maaten (ref54) 2008; 9 caron (ref44) 2020 zhong (ref49) 2022 |
References_xml | – ident: ref15 doi: 10.1109/TGRS.2017.2776357 – year: 2022 ident: ref48 article-title: Vision models are more robust and fair when pretrained on uncurated images without supervision contributor: fullname: goyal – ident: ref30 doi: 10.1109/TGRS.2021.3057768 – ident: ref59 doi: 10.1109/ICCV.2017.74 – ident: ref22 doi: 10.1109/JSTARS.2020.3044643 – start-page: 21271 year: 2020 ident: ref42 article-title: Bootstrap your own latent-A new approach to self-supervised learning publication-title: Proc Adv Neural Inf Process Syst contributor: fullname: grill – ident: ref7 doi: 10.1016/j.patcog.2020.107787 – ident: ref31 doi: 10.1109/JSTARS.2020.3036602 – ident: ref47 doi: 10.1109/CVPR52688.2022.01617 – start-page: 1 year: 2019 ident: ref24 article-title: Using self-supervised learning can improve model robustness and uncertainty publication-title: Proc Adv Neural Inf Process Syst contributor: fullname: hendrycks – ident: ref21 doi: 10.1109/JSTARS.2022.3155406 – volume: 60 year: 2022 ident: ref2 article-title: EFTL: Complex convolutional networks with electromagnetic feature transfer learning for SAR target recognition publication-title: IEEE Trans Geosci Remote Sens contributor: fullname: liu – ident: ref23 doi: 10.1109/JSTARS.2020.3038683 – volume: 19 year: 2022 ident: ref57 article-title: SAR image classification using contrastive learning and pseudo-labels with limited data publication-title: IEEE Geosci Remote Sens Lett contributor: fullname: wang – ident: ref8 doi: 10.1109/TGRS.2021.3076446 – ident: ref4 doi: 10.1007/s41651-019-0042-1 – ident: ref28 doi: 10.1109/JSTARS.2021.3090418 – ident: ref12 doi: 10.1109/LGRS.2018.2877599 – ident: ref43 doi: 10.1109/CVPR46437.2021.01549 – ident: ref58 doi: 10.3390/rs14184632 – ident: ref17 doi: 10.1109/JSTARS.2020.3039235 – volume: 9 start-page: 2579 year: 2008 ident: ref54 article-title: Visualizing data using t-SNE publication-title: Mach Learn Res contributor: fullname: van der maaten – ident: ref19 doi: 10.1109/JSTARS.2021.3104267 – ident: ref35 doi: 10.1109/CVPR42600.2020.00674 – start-page: 69 year: 2016 ident: ref33 article-title: Unsupervised learning of visual representations by solving jigsaw puzzles publication-title: Proc Eur Conf Comput Vis contributor: fullname: noroozi – volume: 19 year: 2021 ident: ref14 article-title: Multilevel wavelet-srnet for SAR target recognition publication-title: IEEE Geosci Remote Sens Lett contributor: fullname: qin – start-page: 9912 year: 2020 ident: ref44 article-title: Unsupervised learning of visual features by contrasting cluster assignments publication-title: Proc Adv Neural Inf Process Syst contributor: fullname: caron – start-page: 1597 year: 2020 ident: ref39 article-title: A simple frame-work for contrastive learning of visual representations publication-title: Proc Int Conf Mach Learn contributor: fullname: chen – ident: ref41 doi: 10.1609/aaai.v36i1.19972 – ident: ref5 doi: 10.1109/JSTARS.2021.3104726 – ident: ref53 doi: 10.1109/IGARSS.2015.7326637 – ident: ref50 doi: 10.1109/JSTARS.2022.3162641 – ident: ref9 doi: 10.1109/IGARSS.2017.8128201 – ident: ref13 doi: 10.1109/LGRS.2018.2865608 – ident: ref40 doi: 10.1109/CVPR42600.2020.00975 – ident: ref18 doi: 10.1109/JSTARS.2021.3059991 – ident: ref55 doi: 10.3390/rs12091385 – ident: ref25 doi: 10.1109/CVPR46437.2021.00113 – ident: ref1 doi: 10.1109/TGRS.2016.2551720 – start-page: 5997 year: 2021 ident: ref46 article-title: Improving contrastive learning on imbalanced data via open-world sampling publication-title: Proc Adv Neural Inf Process Syst contributor: fullname: jiang – ident: ref29 doi: 10.1109/JSTARS.2021.3063335 – ident: ref52 doi: 10.1109/JSTARS.2020.2973920 – ident: ref45 doi: 10.1109/TGRS.2022.3192256 – ident: ref34 doi: 10.1109/CVPR52688.2022.00203 – ident: ref38 doi: 10.1109/CVPR.2018.00393 – ident: ref6 doi: 10.1109/JSTARS.2021.3050108 – ident: ref3 doi: 10.1109/LGRS.2021.3132020 – start-page: 1 year: 2018 ident: ref36 article-title: Unsupervised representation learning by predicting image rotations publication-title: Proc Int Conf Learn Representations contributor: fullname: gidaris – ident: ref32 doi: 10.1007/978-3-319-46487-9_40 – ident: ref27 doi: 10.1109/JSTARS.2021.3056883 – ident: ref16 doi: 10.1109/TGRS.2021.3100137 – start-page: 4003 year: 2020 ident: ref26 article-title: Self-supervised relational reasoning for representation learning publication-title: Proc Adv Neural Inf Process Syst contributor: fullname: patacchiola – ident: ref20 doi: 10.1109/LGRS.2017.2698213 – ident: ref10 doi: 10.1109/IGARSS.2018.8519431 – ident: ref37 doi: 10.1109/CVPR.2006.100 – start-page: 1 year: 2022 ident: ref49 article-title: Is self-supervised contrastive learning more robust than supervised learning? publication-title: Proc Int Conf Mach Learn contributor: fullname: zhong – ident: ref56 doi: 10.1109/TIP.2021.3104179 – ident: ref51 doi: 10.1109/JSTARS.2019.2907655 – ident: ref11 doi: 10.1109/LGRS.2015.2513754 |
SSID | ssj0062793 |
Score | 2.3732262 |
Snippet | Deep-learning-based on convolutional neural networks (CNN) has been widely applied in synthetic aperture radar (SAR) target recognition and made significant... |
SourceID | doaj proquest crossref ieee |
SourceType | Open Website Aggregation Database Publisher |
StartPage | 3915 |
SubjectTerms | Alignment Artificial neural networks Consistency Convolutional neural networks Deep learning Dual consistency alignment (DCA) Learning Machine learning Neural networks Noise Noise intensity Noise threshold Radar polarimetry SAR (radar) Self-supervised learning self-supervised learning (SSL) Speckle speckle noise Synthetic aperture radar synthetic aperture radar (SAR) Target recognition Testing Training |
SummonAdditionalLinks | – databaseName: IEEE Electronic Library Online dbid: RIE link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1Lb9QwEB7RSkhcgEIRCwX5wJEEO3Fi-7gFSsVhD7ut6M2yHbtUXe1WbXJof33HjoN4CKm3JI5lO_P6xhnPAHxwlWSis6wQbUcLbk1dSCtdoUyo0eGS1vgUILtoj0_597PmLB9WT2dhvPcp-MyX8TL9y--2bohbZSjhjNYIkHdgR9JqPKw1qd22EinDLgISVcScMTnFEKPqE_L4fLkqY6XwEuEKGkX-hxlK2fpzeZV_dHIyNEfPYDFNcYwvuSyH3pbu7q_sjQ9ew3N4miEnmY88sgeP_OYFPP6WSvrevoTrLwO2psKdNxFA35L5-uI8BQmQQ7RxHVn5dShWw1VUK_E-52Q9Jwh4yWq-JCcpnJwsp2Ck7Yb8uOh_kljc_nLtyWKL_bA5jhC5bB9Oj76efD4uciWGwqH_16O3qjz3ggdngmpdbYMXIahQNQEBQqgESnVgjbBtI4xBQjS1r9DRQuG2KOKyfgW7m-3GvwbCnaBGoirwQUV0IGVLrWemYwb5wjQz-DgRRl-NCTd0clSo0iMddaSjznScwWEk3q9XY7bs9AA_us7Cp9uOy9BZxZmj3BiOkNixJogW-dMHymawHwn123gjjWZwMPGCzqJ9oyuJirlucG1v_tPtLTyJUxw3ag5gt78e_DuELr19n1j2HrSl6dc priority: 102 providerName: IEEE |
Title | Dual Consistency Alignment Based Self-Supervised Learning for SAR Target Recognition With Speckle Noise Resistance |
URI | https://ieeexplore.ieee.org/document/10103576 https://www.proquest.com/docview/2808835863/abstract/ https://doaj.org/article/6d48fdb941c04aa4916c15f766d0ef01 |
Volume | 16 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3NT4MwFG_MEhMvxo8Zp9P04FEmhZaWI1Pn4mGH4aK3poVWjQtbdDvsv_e1gNF48OIRCpS-7x-8vofQRREJwktNAp6UYUC1igOhRRGkysYAuIRWxifITpLxjN4_sadvrb5cTlhdHrgm3FVSUmFLnVJShFQpCuFMQZjlCTzbtDu3CGvBVG2DkwjErqkxRML0CoQ8m-YD1yp8APEKeEX6ww_5cv1Nf5VfRtl7mtEe2m1CRJzVr7aPtkx1gLbvfAvezSF6v1nDqG-0-eEC3g3O5q_P_qc-HoJPKnFu5jbI10tnBtxxU0P1GUOAivNsih98-jeetslDiwo_vq5esGtG_zY3eLKA-2DYzeCkootmo9uH63HQdE4ICsBrK0CXqaGGU1somyZFrK3h1qY2YhYcuo04aKEljOuEcaWAViw2EQAjUEYNKiniI9SpFpU5RpgWPFQCVNfY1HlzIZJQG6JKooCPivXQZUtHuawLZEgPLMJU1mSXjuyyIXsPDR2tvy511a39CeC5bHgu_-J5D3Udp77NR8IYgFMP9VvWyUYVP2QkwJDGDNZ28h9zn6Idt576K0wfdVbva3MGcclKn3sRPPdbCD8BkwnfIg |
link.rule.ids | 315,786,790,802,870,2115,4043,27956,27957,27958,55109 |
linkProvider | Directory of Open Access Journals |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1Lb9QwEB5BEYILz1YsFPCBIwlx4sT2cQuUBcoedreiN8t27FJ1tVu1yaH8esaOg3gIiVsS24qdeX3jjGcAXtlSUN4amvGmLTJmdJUJI2wmta_Q4RJGuxggO29mx-zTSX2SDqvHszDOuRh85vJwGf_lt1vbh60ylHBaVAiQb8ItNPSFHI5rjYq3KXnMsYuQRGYha0xKMoQd3yCXTxfLPNQKzxGwoFlkvxmimK8_FVj5SytHU3N4H-bjJIcIk_O870xuv_-Rv_G_V_EA7iXQSaYDlzyEG27zCG5_iEV9rx_D5bseW2PpzqsAoa_JdH12GsMEyAFauZYs3dpny_4iKJZwn7KynhKEvGQ5XZBVDCgnizEcabshX8-6bySUtz9fOzLf4jhsDm8IfLYLx4fvV29nWarFkFn0ADv0V6VjjjNvtZeNrYx33Hvpy9ojRPAlR7n2tOamqbnWSIi6ciW6WijeBoVcVHuws9lu3BMgzPJCC1QGzsuAD4RoCuOobqlGztD1BF6PhFEXQ8oNFV2VQqqBjirQUSU6TuAgEO9n15AvOz7Aj66S-KmmZcK3RjJqC6Y1Q1Bsae15gxzqfEEnsBsI9cv7BhpNYH_kBZWE-0qVAlVzVePanv5j2Eu4M1t9OVJHH-efn8HdMN1h22YfdrrL3j1HINOZF5F9fwAyV-0t |
openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Dual+Consistency+Alignment+Based+Self-Supervised+Learning+for+SAR+Target+Recognition+With+Speckle+Noise+Resistance&rft.jtitle=IEEE+journal+of+selected+topics+in+applied+earth+observations+and+remote+sensing&rft.au=Zhai%2C+Yikui&rft.au=Liao%2C+Jinrui&rft.au=Sun%2C+Bing&rft.au=Jiang%2C+Ziyi&rft.date=2023&rft.issn=1939-1404&rft.eissn=2151-1535&rft.volume=16&rft.spage=3915&rft.epage=3928&rft_id=info:doi/10.1109%2FJSTARS.2023.3267824&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_JSTARS_2023_3267824 |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1939-1404&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1939-1404&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1939-1404&client=summon |