OPT OpenIR  > 光学影像学习与分析中心
TLR: Transfer Latent Representation for Unsupervised Domain Adaptation
Xiao, Pan1; Du, Bo1; Wu, Jia2; Zhang, Lefei1; Hu, Ruimin1; Li, Xuelong3
2018-10-08
Conference Name2018 IEEE International Conference on Multimedia and Expo, ICME 2018
Source Publication2018 IEEE International Conference on Multimedia and Expo, ICME 2018
Volume2018-July
Conference Date2018-07-23
Conference PlaceSan Diego, CA, United states
PublisherIEEE Computer Society
Contribution Rank3
AbstractDomain adaptation refers to the process of learning prediction models in a target domain by making use of data from a source domain. Many classic methods solve the domain adaptation problem by establishing a common latent space, which may cause the loss of many important properties across both domains. In this manuscript, we develop a novel method, transfer latent representation (TLR), to learn a better latent space. Specifically, we design an objective function based on a simple linear autoencoder to derive the latent representations of both domains. The encoder in the autoencoder aims to project the data of both domains into a robust latent space. Besides, the decoder imposes an additional constraint to reconstruct the original data, which can preserve the common properties of both domains and reduce the noise that causes domain shift. Experiments on cross-domain tasks demonstrate the advantages of TLR over competing methods. © 2018 IEEE.
Department光学影像学习与分析中心;
DOI10.1109/ICME.2018.8486513
Indexed ByEI
ISBN9781538617373
Language英语
ISSN19457871;1945788X
EI Accession Number20190706509197
Citation statistics
Document Type会议论文
Identifierhttp://ir.opt.ac.cn/handle/181661/31262
Collection光学影像学习与分析中心
Corresponding AuthorDu, Bo
Affiliation1.School of Computer, Wuhan University, Wuhan, Hubei; 430072, China;
2.Department of Computing, Macquarie University, Sydney; NSW; 2109, Australia;
3.Chinese Academy of Sciences, Xi'An Institute of Optics and Precision Mechanics, Xi'an, Shaanxi; 710119, China
Recommended Citation
GB/T 7714
Xiao, Pan,Du, Bo,Wu, Jia,et al. TLR: Transfer Latent Representation for Unsupervised Domain Adaptation[C]:IEEE Computer Society,2018.
Files in This Item:
File Name/Size DocType Version Access License
TLR Transfer Latent (1794KB)会议论文 开放获取CC BY-NC-SAApplication Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Xiao, Pan]'s Articles
[Du, Bo]'s Articles
[Wu, Jia]'s Articles
Baidu academic
Similar articles in Baidu academic
[Xiao, Pan]'s Articles
[Du, Bo]'s Articles
[Wu, Jia]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Xiao, Pan]'s Articles
[Du, Bo]'s Articles
[Wu, Jia]'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.