arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2002.08681cs.LGcs.CVstat.ML
收藏

无监督多类领域自适应:理论、算法与实践

Unsupervised Multi-Class Domain Adaptation: Theory, Algorithms, and Practice

South China University of Technology(华南理工大学);Pazhou Lab(琶洲实验室);The Hong Kong Polytechnic University(香港理工大学);DAMO Academy, Alibaba Group(阿里巴巴集团达摩院)

Yabin Zhang, Bin Deng, Hui Tang, Lei Zhang, Kui Jia

摘要:

在本文中,我们研究了无监督的多类领域自适应(多类UDA)的形式主义,这是最近的一些算法,其学习目标只出于经验。多类评分不一致(MCSD)分歧是通过聚合多类分类中的绝对边缘违规来表示的,该分歧能够充分刻画任意一对多类评分假设之间的关系.通过使用MCSD作为域距离的度量,我们为多类UDA开发了一个新的领域自适应范围;它的数据依赖性,可能近似正确的范围也被开发出来,这自然表明对抗性学习目标可以在源域和目标域之间对齐条件特征分布。因此,多类领域对抗学习网络(McDalNets)的算法框架的开发,其不同的实例通过代理学习目标,要么符合或类似于一些最近流行的方法,从而(部分)强调其实际有效性。基于多类UDA的恒等式理论,我们还提出了一种新的域对称网络算法(SymmNets),该算法具有一种新的域混淆和区分的对抗策略。SymmNets提供了简单的扩展,这些扩展在闭集、部分或开集UDA的问题设置下都能很好地工作。我们进行仔细的实证研究,比较不同的算法McDalNets和我们新推出的SymmNets。实验验证了我们的理论分析,并显示我们提出的对称网络的有效性。此外,我们还公开了我们的实现代码。

英文摘要:

In this paper, we study the formalism of unsupervised multi-class domain adaptation (multi-class UDA), which underlies a few recent algorithms whose learning objectives are only motivated empirically. Multi-Class Scoring Disagreement (MCSD) divergence is presented by aggregating the absolute margin violations in multi-class classification, and this proposed MCSD is able to fully characterize the relations between any pair of multi-class scoring hypotheses. By using MCSD as a measure of domain distance, we develop a new domain adaptation bound for multi-class UDA; its data-dependent, probably approximately correct bound is also developed that naturally suggests adversarial learning objectives to align conditional feature distributions across source and target domains. Consequently, an algorithmic framework of Multi-class Domain-adversarial learning Networks (McDalNets) is developed, and its different instantiations via surrogate learning objectives either coincide with or resemble a few recently popular methods, thus (partially) underscoring their practical effectiveness. Based on our identical theory for multi-class UDA, we also introduce a new algorithm of Domain-Symmetric Networks (SymmNets), which is featured by a novel adversarial strategy of domain confusion and discrimination. SymmNets affords simple extensions that work equally well under the problem settings of either closed set, partial, or open set UDA. We conduct careful empirical studies to compare different algorithms of McDalNets and our newly introduced SymmNets. Experiments verify our theoretical analysis and show the efficacy of our proposed SymmNets. In addition, we have made our implementation code publicly available.

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。

↑