arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.01656cs.CV
收藏

广义领域自适应

Generalized Domain Adaptation

NTT Corporation(日本电信电话公司);NTT Communication Science Laboratories(NTT通信科学实验室)

Yu Mitsuzumi, Go Irie, Daiki Ikami, Takashi Shibata

摘要:

无监督领域自适应(UDA)问题的许多变体已经被提出并单独解决。它的副作用是,适用于一种变体的方法往往对另一种变体无效,甚至不适用,这阻碍了实际应用。本文给出了UDA问题的一般表示,称为广义领域自适应(GDA)。GDA将主要变量作为特殊情况来涵盖,这使我们能够将它们组织在一个全面的框架中。此外,这种泛化导致了一个新的具有挑战性的设置,其中现有的方法失败,例如当域标签是未知的,并且类标签仅部分地给予每个域时。我们提出了一种新的方法,新的设置。我们方法的关键是自监督类破坏性学习,它可以在不使用任何域标签的情况下学习类不变表示和域对抗分类器。使用三个基准数据集进行的大量实验表明,我们的方法在新的设置中优于最先进的UDA方法,并且在现有的UDA变体中也具有竞争力。

英文摘要:

Many variants of unsupervised domain adaptation (UDA) problems have been proposed and solved individually. Its side effect is that a method that works for one variant is often ineffective for or not even applicable to another, which has prevented practical applications. In this paper, we give a general representation of UDA problems, named Generalized Domain Adaptation (GDA). GDA covers the major variants as special cases, which allows us to organize them in a comprehensive framework. Moreover, this generalization leads to a new challenging setting where existing methods fail, such as when domain labels are unknown, and class labels are only partially given to each domain. We propose a novel approach to the new setting. The key to our approach is self-supervised class-destructive learning, which enables the learning of class-invariant representations and domain-adversarial classifiers without using any domain labels. Extensive experiments using three benchmark datasets demonstrate that our method outperforms the state-of-the-art UDA methods in the new setting and that it is competitive in existing UDA variations as well.

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。

↑