OPT OpenIR  > 光学影像学习与分析中心
Flexible Affinity Matrix Learning for Unsupervised and Semisupervised Classification
Fang, Xiaozhao1; Han, Na1; Wong, Wai Keung2,3; Teng, Shaohua1; Wu, Jigang1; Xie, Shengli4; Li, Xuelong5,6
Department光学影像学习与分析中心
2019-04
Source PublicationIEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
ISSN2162-237X;2162-2388
Volume30Issue:4Pages:1133-1149
Contribution Rank5
Abstract

In this paper, we propose a unified model called flexible affinity matrix learning (FAML) for unsupervised and semisupervised classification by exploiting both the relationship among data and the clustering structure simultaneously. To capture the relationship among data, we exploit the self-expressiveness property of data to learn a structured matrix in which the structures are induced by different norms. A rank constraint is imposed on the Laplacian matrix of the desired affinity matrix, so that the connected components of data are exactly equal to the cluster number. Thus, the clustering structure is explicit in the learned affinity matrix. By making the estimated affinity matrix approximate the structured matrix during the learning procedure, FAML allows the affinity matrix itself to be adaptively adjusted such that the learned affinity matrix can well capture both the relationship among data and the clustering structure. Thus, FAML has the potential to perform better than other related methods. We derive optimization algorithms to solve the corresponding problems. Extensive unsupervised and semisupervised classification experiments on both synthetic data and real-world benchmark data sets show that the proposed FAML consistently outperforms the state-of-the-art methods.

KeywordAffinity matrix clustering low-rank representation (LRR) sparse representation
DOI10.1109/TNNLS.2018.2861839
Indexed BySCI
Language英语
WOS IDWOS:000461854100013
PublisherIEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Citation statistics
Document Type期刊论文
Identifierhttp://ir.opt.ac.cn/handle/181661/31349
Collection光学影像学习与分析中心
Corresponding AuthorWong, Wai Keung
Affiliation1.Guangdong Univ Technol, Sch Comp Sci & Technol, Guangzhou 510006, Guangdong, Peoples R China
2.Hong Kong Polytech Univ, Inst Text & Clothing, Hong Kong, Peoples R China
3.Hong Kong Polytech Univ, Shenzhen Res Inst, Shenzhen 518055, Peoples R China
4.Guangdong Univ Technol, Sch Automat, Guangzhou 510006, Guangdong, Peoples R China
5.Chinese Acad Sci, Xian Inst Opt & Precis Mech, Xian 710119, Shaanxi, Peoples R China
6.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
Recommended Citation
GB/T 7714
Fang, Xiaozhao,Han, Na,Wong, Wai Keung,et al. Flexible Affinity Matrix Learning for Unsupervised and Semisupervised Classification[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2019,30(4):1133-1149.
APA Fang, Xiaozhao.,Han, Na.,Wong, Wai Keung.,Teng, Shaohua.,Wu, Jigang.,...&Li, Xuelong.(2019).Flexible Affinity Matrix Learning for Unsupervised and Semisupervised Classification.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,30(4),1133-1149.
MLA Fang, Xiaozhao,et al."Flexible Affinity Matrix Learning for Unsupervised and Semisupervised Classification".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 30.4(2019):1133-1149.
Files in This Item:
File Name/Size DocType Version Access License
Flexible Affinity Ma(4698KB)期刊论文出版稿开放获取CC BY-NC-SAView Application Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Fang, Xiaozhao]'s Articles
[Han, Na]'s Articles
[Wong, Wai Keung]'s Articles
Baidu academic
Similar articles in Baidu academic
[Fang, Xiaozhao]'s Articles
[Han, Na]'s Articles
[Wong, Wai Keung]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Fang, Xiaozhao]'s Articles
[Han, Na]'s Articles
[Wong, Wai Keung]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Flexible Affinity Matrix Learning for Unsupervised and Semisupervised Classification.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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