CASIA OpenIR  > 智能感知与计算研究中心
Distant Supervised Centroid Shift: A Simple and Efficient Approach to Visual Domain Adaptation
Jian Liang1,2; Ran He1,2,3; Zhenan Sun1,2,3; Tieniu Tan1,2,3
Conference NameIEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Conference Date2019
Conference PlaceUSA

    Conventional domain adaptation methods usually resort to deep neural networks or subspace learning to find invariant representations across domains.
    However, most deep learning methods highly rely on large-size source domains and are computationally expensive to train, while subspace learning methods always have a quadratic time complexity that suffers from the large domain size. 
    This paper provides a simple and efficient solution, which could be regarded as a well-performing baseline for domain adaptation tasks.
    Our method is built upon the nearest centroid classifier, seeking a subspace where the centroids in the target domain are moderately shifted from those in the source domain.
    Specifically, we design a unified objective without accessing the source domain data and adopt an alternating minimization scheme to iteratively discover the pseudo target labels, invariant subspace, and target centroids.
    Besides its privacy-preserving property (distant supervision), the algorithm is provably convergent and has a promising linear time complexity.       
    In addition, the proposed method can be readily extended to multi-source setting and domain generalization, and it remarkably enhances popular deep adaptation methods by borrowing the learned transferable features.
    Extensive experiments on several benchmarks including object, digit, and face recognition datasets validate that our methods yield state-of-the-art results in various domain adaptation tasks.

KeywordDomain Adaptation
Indexed ByEI
Document Type会议论文
Affiliation1.CRIPAC \& NLPR, Institute of Automation, Chinese Academy of Sciences (CAS)
2.CAS Center for Excellence in Brain Science and Intelligence Technology
3.University of Chinese Academy of Sciences
First Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Jian Liang,Ran He,Zhenan Sun,et al. Distant Supervised Centroid Shift: A Simple and Efficient Approach to Visual Domain Adaptation[C],2019.
Files in This Item: Download All
File Name/Size DocType Version Access License
1847.pdf(607KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Jian Liang]'s Articles
[Ran He]'s Articles
[Zhenan Sun]'s Articles
Baidu academic
Similar articles in Baidu academic
[Jian Liang]'s Articles
[Ran He]'s Articles
[Zhenan Sun]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Jian Liang]'s Articles
[Ran He]'s Articles
[Zhenan Sun]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 1847.pdf
Format: Adobe PDF
All comments (0)
No comment.

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