CASIA OpenIR
Exploring uncertainty in pseudo-label guided unsupervised domain adaptation
Liang, Jian1,2,3; He, Ran1,3,4; Sun, Zhenan1,3,4; Tan, Tieniu1,3,4
Source PublicationPATTERN RECOGNITION
ISSN0031-3203
2019-12-01
Volume96Pages:11
Corresponding AuthorLiang, Jian(liangjian92@gmail.com)
AbstractDue to the unavailability of labeled target data, most existing unsupervised domain adaptation (UDA) methods alternately classify the unlabeled target samples and discover a low-dimensional subspace by mitigating the cross-domain distribution discrepancy. During the pseudo-label guided subspace discovery step, however, the posterior probabilities (uncertainties) from the previous target label estimation step are totally ignored, which may promote the error accumulation and degrade the adaptation performance. To address this issue, we propose to progressively increase the number of target training samples and incorporate the uncertainties to accurately characterize both cross-domain distribution discrepancy and other infra-domain relations. Specifically, we exploit maximum mean discrepancy (MMD) and within class variance minimization for these relations, yet, these terms merely focus on the global class structure while ignoring the local structure. Then, a triplet-wise instance-to-center margin is further maximized to push apart target instances and source class centers of different classes and bring closer them of the same class. Generally, an EM-style algorithm is developed by alternating between inferring uncertainties, progressively selecting certain training target samples, and seeking the optimal feature transformation to bridge two domains. Extensive experiments on three popular visual domain adaptation datasets demonstrate that our method significantly outperforms recent state-of-the-art approaches. (C) 2019 Elsevier Ltd. All rights reserved.
KeywordUnsupervised domain adaptation Pseudo labeling Feature transformation Progressive learning Transfer learning
DOI10.1016/j.patcog.2019.106996
WOS KeywordKERNEL
Indexed BySCI
Language英语
Funding ProjectState Key Development Program[2016YFB1001001] ; National Natural Science Foundation of China[61622310] ; National Natural Science Foundation of China[61473289]
Funding OrganizationState Key Development Program ; National Natural Science Foundation of China
WOS Research AreaComputer Science ; Engineering
WOS SubjectComputer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS IDWOS:000487569700042
PublisherELSEVIER SCI LTD
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/26442
Collection中国科学院自动化研究所
Corresponding AuthorLiang, Jian
Affiliation1.Chinese Acad Sci CASIA, Inst Automat, Natl Lab Pattern Recognit, Ctr Res Intelligent Percept & Comp, Beijing, Peoples R China
2.NUS, Dept ECE, Singapore, Singapore
3.UCAS, Beijing, Peoples R China
4.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Beijing, Peoples R China
First Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Corresponding Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Liang, Jian,He, Ran,Sun, Zhenan,et al. Exploring uncertainty in pseudo-label guided unsupervised domain adaptation[J]. PATTERN RECOGNITION,2019,96:11.
APA Liang, Jian,He, Ran,Sun, Zhenan,&Tan, Tieniu.(2019).Exploring uncertainty in pseudo-label guided unsupervised domain adaptation.PATTERN RECOGNITION,96,11.
MLA Liang, Jian,et al."Exploring uncertainty in pseudo-label guided unsupervised domain adaptation".PATTERN RECOGNITION 96(2019):11.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Liang, Jian]'s Articles
[He, Ran]'s Articles
[Sun, Zhenan]'s Articles
Baidu academic
Similar articles in Baidu academic
[Liang, Jian]'s Articles
[He, Ran]'s Articles
[Sun, Zhenan]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Liang, Jian]'s Articles
[He, Ran]'s Articles
[Sun, Zhenan]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.