Class conditional distribution alignment for domain adaptation

CSpace

	Class conditional distribution alignment for domain adaptation
	Kai CAO 1; Zhipeng TU 1; Yang MING 1
	2020-01-01
Source Publication	控制理论与技术:英文版
ISSN	2095-6983
Volume	18.0 Issue:1.0 Pages:72-80
Abstract	In this paper,we study the problem of domain adaptation,which is a crucial ingredient in transfer learning with two domains,that is,the source domain with labeled data and the target domain with none or few labels.Domain adaptation aims to extract knowledge from the source domain to improve the performance of the learning task in the target domain.A popular approach to handle this problem is via adversarial training,which is explained by the H△H-distance theory.However,traditional adversarial network architectures just align the marginal feature distribution in the feature space.The alignment of class condition distribution is not guaranteed.Therefore,we proposed a novel method based on pseudo labels and the cluster assumption to avoid the incorrect class alignment in the feature space.The experiments demonstrate that our framework improves the accuracy on typical transfer learning tasks.
Keyword	Domain adaptation distribution alignment feature cluster
Indexed By	CSCD
Language	中文
CSCD ID	CSCD:6709874
Citation statistics
Document Type	期刊论文
Identifier	http://ir.amss.ac.cn/handle/2S8OKBNM/56126
Collection	中国科学院数学与系统科学研究院
Affiliation	1.Key Lab of Systems and Control,Academy of Mathematics and Systems Science,Chinese Academy of Sciences 2.中国科学院大学
Recommended Citation GB/T 7714	Kai CAO,Zhipeng TU,Yang MING. Class conditional distribution alignment for domain adaptation[J]. 控制理论与技术:英文版,2020,18.0(1.0):72-80.
APA	Kai CAO,Zhipeng TU,&Yang MING.(2020).Class conditional distribution alignment for domain adaptation.控制理论与技术:英文版,18.0(1.0),72-80.
MLA	Kai CAO,et al."Class conditional distribution alignment for domain adaptation".控制理论与技术:英文版 18.0.1.0(2020):72-80.

Files in This Item:
There are no files associated with this item.

If you have any objections to this item, please fill out the form below and the administrator will contact you as soon as possible.
Content:
Email：	*
Institution:
Verification Code:	Refresh

Any comments and suggestions are welcomed.
Title:	*
Content:
Email：	*
Verification Code:	Refresh

中国科学院数学与系统科学研究院机构知识库