English  |  正體中文  |  简体中文  |  全文笔数/总笔数 : 62570/95233 (66%)
造访人次 : 2560098      在线人数 : 279
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library & TKU Library IR team.
搜寻范围 查询小技巧:
  • 您可在西文检索词汇前后加上"双引号",以获取较精准的检索结果
  • 若欲以作者姓名搜寻,建议至进阶搜寻限定作者字段,可获得较完整数据
  • 进阶搜寻

    jsp.display-item.identifier=請使用永久網址來引用或連結此文件: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/122961

    题名: Domain-Invariant Feature Learning for Domain Adaptation
    作者: Tu, Ching-Ting;Lin, Hsiau-Wen;Lin, Hwei Jen;Tokuyama, Yoshimasa;Chu, Chia-Hung
    关键词: cross domain adaption (CDA);target domain;source domain;domain invariant feature;generative adversarial network (GAN);maximum mean discrepancy (MMD)
    日期: 2023-02-15
    上传时间: 2023-04-28 16:32:42 (UTC+8)
    出版者: World Scientific Publishing Co. Pte. Ltd.
    摘要: Unsupervised domain adaptation (UDA) explores mainly how to learn domain-invariant features from the source domain when the target domain label is unknown. To learn domain-invariant features requires aligning the distribution of samples from two domains in the feature space, which can be achieved by minimizing the maximum mean discrepancy (MMD) of samples from the two domains. However, there is still no effective way to find the best parameter values of MMD. Such a problem is addressed in the MMD with deep kernels (MMD-D), whose optimal parameters can be obtained through training. This study proposes a method of domain-invariant feature learning for UDA, whose architecture, named MMDDCDA, comprises a MMD-D module and a CDA (Cross Domain Adaptation) module. MMDDCDA performs alternating training similar to adversarial training to alternately alternatively boost the power of the two modules. To our knowledge, this is the first UDA method that performs such alternating training on a UDA architecture using MMD with deep kernels. Experimental validation showed that the proposed method yields state-of-the-art results among UDA methods using other MMD variants and some UDA benchmarks.
    關聯: International Journal of Pattern Recognition and Artificial Intelligence
    显示于类别:[資訊工程學系暨研究所] 期刊論文


    档案 大小格式浏览次数
    Domain-Invariant Feature Learning for Domain Adaptation.html0KbHTML21检视/开启



    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library & TKU Library IR teams. Copyright ©   - 回馈