...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Neurocomputing >Adversarial open set domain adaptation via progressive selection of transferable target samples
【24h】

Adversarial open set domain adaptation via progressive selection of transferable target samples

机译：通过逐步选择可转移目标样本的对抗开放式域适应

获取原文
获取原文并翻译 | 示例
   

获取外文期刊封面封底 >>

       
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

In recent years, many Unsupervised Domain Adaptation (UDA) methods have been proposed to tackle the domain shift problem. Most existing UDA methods are derived for Close Set Domain Adaptation (CSDA) in which source and target domains are assumed to share the same label space. However, target domain may contain unknown class different from the known ones in the source domain in practice, i.e., Open Set Domain Adaptation (OSDA). Due to the presence of unknown class, aligning the whole distribution of the source and target domain for OSDA as in the previous methods will lead to negative transfer. Existing methods developed for OSDA attempt to assign smaller weights to target samples of unknown class. Despite promising performance achieved by existing methods, the samples of the unknown class are still used for distribution alignment, which makes the model suffer from the risk of negative transfer. Instead of reweighting, this paper presents a novel method namely Thresholded Domain Adversarial Network (ThDAN), which progressively selects transferable target samples for distribution alignment. Based on the fact that samples from the known classes must be more transferable than target samples of the unknown one, we derive a criterion to quantify the transferability by constructing classifiers to categorize known classes and to discriminate unknown class. In ThDAN, an adaptive threshold is calculated by averaging transferability scores of source domain samples to select target samples for training. The threshold is tweaked progressively during the training process so that more and more target samples from the known classes can be correctly selected for adversarial training. Extensive experiments show that the proposed method outperforms state-of-the-art domain adaptation and open set recognition approaches on benchmarks. (C) 2020 Elsevier B.V. All rights reserved.
机译：近年来，已经提出了许多无监督的域适应（UDA）方法来解决域移位问题。派生大多数现有的UDA方法用于关闭设置域适配（CSDA），其中假设源和目标域共享相同的标签空间。然而，目标域可以包含在实践中的源域中的已知类别不同的​​未知类，即，开放集域适应（OSDA）。由于存在未知类，对准OSDA的源域的整体分布，如先前的方法将导致负转移。为OSDA开发的现有方法尝试将较小的权重分配给未知类的目标样本。尽管现有方法实现了有希望的性能，但是未知类的样本仍然用于分布对准，这使得模型遭受负转移的风险。本文提出了一种新的方法即阈值域对抗网络（Thdan）的新方法，其逐渐选择用于分布对准的可转移目标样本。基于来自已知类别的样本必须比未知的目标样本更可转移，我们推导了一种标准来通过构建分类器来对已知类分类并辨别未知类来量化的标准来量化可转换性。在THDAN中，通过平均源域样本的可转换分数来计算自适应阈值以选择用于训练的目标样本。在训练过程中逐步调整阈值，以便可以正确地选择来自已知类别的越来越多的目标样本用于对抗训练。广泛的实验表明，该方法优于最先进的域适应和开放式识别方法在基准上。 （c）2020 Elsevier B.v.保留所有权利。

著录项

  • 来源
    《Neurocomputing》 |2020年第14期|174-184|共11页
  • 作者

    Gao Yuan; Ma Andy J.; Gao Yue; Wang Jinpeng; Pan YoungSun;

  • 作者单位

    Sun Yat Sen Univ Sch Data & Comp Sci Guangzhou Peoples R China;

    Sun Yat Sen Univ Sch Data & Comp Sci Guangzhou Peoples R China|Minist Educ Key Lab Machine Intelligence & Adv Comp Guangzhou Peoples R China;

    Sun Yat Sen Univ Sch Data & Comp Sci Guangzhou Peoples R China;

    Sun Yat Sen Univ Sch Elect & Informat Technol Guangzhou Peoples R China;

    Sun Yat Sen Univ Sch Data & Comp Sci Guangzhou Peoples R China;

  • 收录信息 美国《科学引文索引》(SCI);美国《工程索引》(EI);
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    Open set domain adaptation; Adversarial learning; Progressive selection;

    机译：开放式域适应;对抗学习;渐进式选择;

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号