arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.01708cs.CV
收藏

基于关键语义分类器的无监督领域自适应对抗学习

Crucial Semantic Classifier-based Adversarial Learning for Unsupervised Domain Adaptation

Baidu Inc.(百度公司);Shenyang Institute of Automation, Chinese Academy of Sciences(中国科学院沈阳自动化研究所);University of Science and Technology of China(中国科学技术大学);Hunan University(湖南大学);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所)

Yumin Zhang, Yajun Gao, Hongliu Li, Ating Yin, Duzhen Zhang, Xiuyi Chen

摘要:

无监督领域自适应(UDA)是一种旨在探索从一个已标记的源域到一个相关的未标记的目标域的可转移特征的方法,已经得到了广泛的发展。然而,作为主流方法之一,现有的基于对抗的方法忽略了过滤无关的语义知识,阻碍了自适应性能的提高。此外,它们还需要一个额外的域映射器,以使提取器产生混乱的表示,但离散设计可能会导致模型崩溃。为了解决上述问题,我们提出了基于关键语义分类器的对抗学习(CSCAL),它更加关注关键语义知识的传递,并利用分类器隐含地扮演领域鉴别器的角色,而无需额外的网络设计。具体来说,在类内对齐中,设计了一个配对级别离散(PLD)来传递关键的语义知识。此外,基于分类器的预测,一个核Norm-based离散(NND)的形成,考虑类间的明智的信息,提高适应性能。此外,CSCAL可以毫不费力地合并到不同的UDA方法作为正则化,并显着提高其性能。

英文摘要:

Unsupervised Domain Adaptation (UDA), which aims to explore the transferrable features from a well-labeled source domain to a related unlabeled target domain, has been widely progressed. Nevertheless, as one of the mainstream, existing adversarial-based methods neglect to filter the irrelevant semantic knowledge, hindering adaptation performance improvement. Besides, they require an additional domain discriminator that strives extractor to generate confused representations, but discrete designing may cause model collapse. To tackle the above issues, we propose Crucial Semantic Classifier-based Adversarial Learning (CSCAL), which pays more attention to crucial semantic knowledge transferring and leverages the classifier to implicitly play the role of domain discriminator without extra network designing. Specifically, in intra-class-wise alignment, a Paired-Level Discrepancy (PLD) is designed to transfer crucial semantic knowledge. Additionally, based on classifier predictions, a Nuclear Norm-based Discrepancy (NND) is formed that considers inter-class-wise information and improves the adaptation performance. Moreover, CSCAL can be effortlessly merged into different UDA methods as a regularizer and dramatically promote their performance.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑