Symmetric low-rank representation for subspace clustering

被引:24
作者
Chen, Jie [1 ]
Zhang, Haixian [1 ]
Mao, Hua [1 ]
Sang, Yongsheng [1 ]
Yi, Zhang [1 ]
机构
[1] Sichuan Univ, Coll Comp Sci, Machine Intelligence Lab, Chengdu 610065, Peoples R China
基金
美国国家科学基金会;
关键词
Subspace clustering; Spectral clustering; Symmetric low-rank representation; Affinity matrix; Low-rank matrix recovery; Dimension reduction; ALGORITHM; SELECTION;
D O I
10.1016/j.neucom.2015.08.077
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We propose a symmetric low-rank representation (SLRR) method for subspace clustering, which assumes that a data set is approximately drawn from the union of multiple subspaces. The proposed technique can reveal the membership of multiple subspaces through the self-expressiveness property of the data. In particular, the SLRR method considers a collaborative representation combined with low-rank matrix recovery techniques as a low-rank representation to learn a symmetric low-rank representation, which preserves the subspace structures of high-dimensional data. In contrast to performing iterative singular value decomposition in some existing low-rank representation based algorithms, the symmetric low-rank representation in the SLRR method can be calculated as a closed form solution by solving the symmetric low-rank optimization problem. By making use of the angular information of the principal directions of the symmetric low-rank representation, an affinity graph matrix is constructed for spectral clustering. Extensive experimental results show that it outperforms state-of-the-art subspace clustering algorithms. (C) 2015 Elsevier B.V. All rights reserved.
引用
收藏
页码:1192 / 1202
页数:11
相关论文
共 49 条
[1]   Nearness to Local Subspace Algorithm for Subspace and Motion Segmentation [J].
Aldroubi, Akram ;
Sekmen, Ali .
IEEE SIGNAL PROCESSING LETTERS, 2012, 19 (10) :704-707
[2]  
[Anonymous], ARXIV12090841
[3]  
[Anonymous], CVPR
[4]  
[Anonymous], CVPR
[5]  
[Anonymous], 2011, P ADV NEUR INF PROC
[6]  
[Anonymous], 2011, ARXIV11071561
[7]   Inductive Robust Principal Component Analysis [J].
Bao, Bing-Kun ;
Liu, Guangcan ;
Xu, Changsheng ;
Yan, Shuicheng .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2012, 21 (08) :3794-3800
[8]   Lambertian reflectance and linear subspaces [J].
Basri, R ;
Jacobs, DW .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2003, 25 (02) :218-233
[9]  
Bingham E., 2001, KDD-2001. Proceedings of the Seventh ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, P245, DOI 10.1145/502512.502546
[10]  
Boult T. E., 1991, Proceedings of the IEEE Workshop on Visual Motion (Cat. No.91TH0390-5), P179, DOI 10.1109/WVM.1991.212809