|
|
【答案】应助回帖
★ ★ ★ ★ ★
感谢参与，应助指数 +1
hopfliking: 金币+5, ★★★★★最佳答案 2014-09-21 19:15:07
sunshan4379: LS-EPI+1, 感谢应助！ 2014-09-21 19:36:50
A fast tri-factorization method for low-rank matrix recovery and completion
作者:Liu, YY (Liu, Yuanyuan)[ 1 ] ; Jiao, LC (Jiao, L. C.)[ 1 ] ; Shang, FH (Shang, Fanhua)[ 1 ]
PATTERN RECOGNITION
卷: 46
期: 1
页: 163-173
DOI: 10.1016/j.patcog.2012.07.003
出版年: JAN 2013
查看期刊信息
摘要
In recent years, matrix rank minimization problems have received a significant amount of attention in machine learning, data mining and computer vision communities. And these problems can be solved by a convex relaxation of the rank minimization problem which minimizes the nuclear norm instead of the rank of the matrix, and has to be solved iteratively and involves singular value decomposition (SVD) at each iteration. Therefore, those algorithms for nuclear norm minimization problems suffer from high computation cost of multiple SVDs. In this paper, we propose a Fast Tri-Factorization (FTF) method to approximate the nuclear norm minimization problem and mitigate the computation cost of performing SVDs. The proposed FTF method can be used to reliably solve a wide range of low-rank matrix recovery and completion problems such as robust principal component analysis (RPCA), low-rank representation (LRR) and low-rank matrix completion (MC). We also present three specific models for RPCA, LRR and MC problems, respectively. Moreover, we develop two alternating direction method (ADM) based iterative algorithms for solving the above three problems. Experimental results on a variety of synthetic and real-world data sets validate the efficiency, robustness and effectiveness of our FTF method comparing with the state-of-the-art nuclear norm minimization algorithms. (C) 2012 Elsevier Ltd. All rights reserved.
关键词
作者关键词:Rank minimization; Nuclear norm minimization; Matrix completion; Low-rank and sparse decomposition; Low rank representation
KeyWords Plus:LINEAR INVERSE PROBLEMS; THRESHOLDING ALGORITHM; FACE RECOGNITION; APPROXIMATION; SEGMENTATION; SUBSPACES
作者信息
通讯作者地址: Liu, YY (通讯作者)
[显示增强组织信息的名称] Xidian Univ, Minist Educ China, Key Lab Intelligent Percept & Image Understanding, Mailbox 224,2 S TaiBai Rd, Xian 710071, Peoples R China.
地址:
[显示增强组织信息的名称] [ 1 ] Xidian Univ, Minist Educ China, Key Lab Intelligent Percept & Image Understanding, Xian 710071, Peoples R China
电子邮件地址:yuanyuanliu0917@yahoo.com.cn; jlcxidian@163.com; shangfanhua@hotmail.com
基金资助致谢
基金资助机构 授权号
National Natural Science Foundation of China
60971112
60971128
60970067
61072108
Fund for Foreign Scholars in University Research and Teaching Programs (111 Project)
B07048
Fundamental Research Funds for the Central Universities
JY10000902001
JY10000902041
JY10000902043
查看基金资助信息
出版商
ELSEVIER SCI LTD, THE BOULEVARD, LANGFORD LANE, KIDLINGTON, OXFORD OX5 1GB, OXON, ENGLAND
类别 / 分类
研究方向:Computer Science; Engineering
Web of Science 类别:Computer Science, Artificial Intelligence; Engineering, Electrical & Electronic
文献信息
文献类型:Article
语种:English
入藏号: WOS:000309785000015
ISSN: 0031-3203
电子 ISSN: 1873-5142
期刊信息
目录： Current Contents Connect®
Impact Factor (影响因子): Journal Citation Reports®
其他信息
IDS 号: 020CA
Web of Science 核心合集中的 "引用的参考文献": 52
Web of Science 核心合集中的 "被引频次": 1 |
|
回复此楼