Item request has been placed! ×
Item request cannot be made. ×
loading  Processing Request

Cross-Domain Urban Land Use Classification via Scenewise Unsupervised Multisource Domain Adaptation with Transformer

Item request has been placed! ×
Item request cannot be made. ×
loading   Processing Request
اقرأ أكثر حفظ في قائمتي
  • المؤلفون: Li, Mengmeng; Zhang, Congcong; Zhao, Wufan; Zhou, Wen
  • نوع التسجيلة:
    Electronic Resource
  • الدخول الالكتروني :
    http://repository.hkust.edu.hk/ir/Record/1783.1-138744
    https://doi.org/10.1109/jstars.2024.3399741
    https://doi.org/10.1109/JSTARS.2024.3399741
    http://lbdiscover.ust.hk/uresolver?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rfr_id=info:sid/HKUST:SPI&rft.genre=article&rft.issn=1939-1404&rft.volume=17&rft.issue=&rft.date=2024&rft.spage=10051&rft.aulast=Li&rft.aufirst=Mengmeng&rft.atitle=Cross-Domain+Urban+Land+Use+Classification+via+Scenewise+Unsupervised+Multisource+Domain+Adaptation+with+Transformer&rft.title=IEEE+Journal+of+Selected+Topics+in+Applied+Earth+Observations+and+Remote+Sensing
    http://www.scopus.com/record/display.url?eid=2-s2.0-85193243653&origin=inward
    http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=LinksAMR&SrcApp=PARTNER_APP&DestLinkType=FullRecord&DestApp=WOS&KeyUT=001236723400007
  • معلومة اضافية
    • Publisher Information:
      Institute of Electrical and Electronics Engineers Inc. 2024
    • نبذة مختصرة :
      Current land use classification models based on very high-resolution (VHR) remote sensing images often suffer from high sample dependence and poor transferability. To address these challenges, we propose an unsupervised multisource domain adaptation framework for cross-domain land use classification that eliminates the need for repeatedly using source domain data. Our method uses the Swin Transformer as the backbone of the source domain model to extract features from multiple source domain samples. The model is trained on source domain samples, and unlabeled target domain samples are then used for target domain model training. To minimize the feature discrepancies between the source and target domains, we use a weighted information maximization loss and self-supervised pseudolabels to alleviate cross-domain classification noise. We conducted experiments on four public scene datasets and four new land use scene datasets created from different VHR images in four Chinese cities. Results show that our method outperformed three existing single-source cross-domain methods (i.e., DANN, DeepCORAL, and DSAN) and four multisource cross-domain methods (i.e., M3SDA, PTMDA, MFSAN, and SHOT), achieving the highest average classification accuracy and strong stability. We conclude that our method has high potential for practical applications in cross-domain land use classification using VHR images. © 2008-2012 IEEE.
    • الموضوع:
      Cross-domain classification; Land use classification; Multisource domain adaptation; Swin transformer; Very high resolution (VHR) remote sensing images; Article
    • Availability:
      Open access content. Open access content
    • Note:
      English
    • Other Numbers:
      HNK oai:repository.hkust.edu.hk:1783.1-138744
      IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, v. 17, May 2024, article number 10529516, p. 10051-10066
      1939-1404
      2151-1535
      1452722220
    • Contributing Source:
      HONG KONG UNIV OF SCI & TECH, THE
      From OAIster®, provided by the OCLC Cooperative.
    • الرقم المعرف:
      edsoai.on1452722220
HoldingsOnline