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

Restoring vision in hazy weather with hierarchical contrastive learning

Item request has been placed! ×
Item request cannot be made. ×
loading   Processing Request
اقرأ أكثر حفظ في قائمتي
  • المؤلفون: Wang, Tao; Tao, Guangpin; Lu, Wanglong; Zhang, Kaihao; Luo, Wenhan; Zhang, Xiaoqin; Lu, Tong
  • نوع التسجيلة:
    Electronic Resource
  • الدخول الالكتروني :
    http://repository.hkust.edu.hk/ir/Record/1783.1-138823
    https://doi.org/10.1016/j.patcog.2023.109956
    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=0031-3203&rft.volume=&rft.issue=&rft.date=2024&rft.spage=&rft.aulast=Wang&rft.aufirst=Tao&rft.atitle=Restoring+vision+in+hazy+weather+with+hierarchical+contrastive+learning&rft.title=Pattern+Recognition
    http://www.scopus.com/record/display.url?eid=2-s2.0-85171772506&origin=inward
    http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=LinksAMR&SrcApp=PARTNER_APP&DestLinkType=FullRecord&DestApp=WOS&KeyUT=001084077900001
  • معلومة اضافية
    • Publisher Information:
      Elsevier Ltd 2024
    • نبذة مختصرة :
      Image restoration under hazy weather condition, which is called single image dehazing, has been of significant interest for various computer vision applications. In recent years, deep learning-based methods have achieved success. However, existing image dehazing methods typically neglect the hierarchy of features in the neural network and fail to exploit their relationships fully. To this end, we propose an effective image dehazing method named Hierarchical Contrastive Dehazing (HCD), which is based on feature fusion and contrastive learning strategies. HCD consists of a hierarchical dehazing network (HDN) and a novel hierarchical contrastive loss (HCL). Specifically, the core design in the HDN is a hierarchical interaction module, which utilizes multi-scale activation to revise the feature responses hierarchically. To cooperate with the training of HDN, we propose HCL which performs contrastive learning on hierarchically paired exemplars, facilitating haze removal. Extensive experiments on public datasets, RESIDE, HazeRD, and DENSE-HAZE, demonstrate that HCD quantitatively outperforms the state-of-the-art methods in terms of PSNR, SSIM and achieves better visual quality. © 2023 Elsevier Ltd
    • الموضوع:
      Contrastive learning; Feature fusion; Hierarchical contrastive loss; Image dehazing; Article
    • Availability:
      Open access content. Open access content
    • Note:
      English
    • Other Numbers:
      HNK oai:repository.hkust.edu.hk:1783.1-138823
      Pattern Recognition, v. 145, January 2024, article number 109956
      0031-3203
      1873-5142
      1452721416
    • Contributing Source:
      HONG KONG UNIV OF SCI & TECH, THE
      From OAIster®, provided by the OCLC Cooperative.
    • الرقم المعرف:
      edsoai.on1452721416
HoldingsOnline