Structured block diagonal representation for subspace clustering

被引:15
作者
Liu, Maoshan [1 ]
Wang, Yan [1 ]
Sun, Jun [2 ]
Ji, Zhicheng [1 ]
机构
[1] Jiangnan Univ, Minist Educ, Engn Res Ctr Internet Things Technol Applicat, 1800 Lihu Ave, Wuxi 214122, Jiangsu, Peoples R China
[2] Jiangnan Univ, Jiangsu Prov Engn Lab Pattern Recognit & Computat, 1800 Lihu Ave, Wuxi 214122, Jiangsu, Peoples R China
基金
国家重点研发计划; 中国国家自然科学基金;
关键词
Subspace clustering; Structured sparse subspace clustering; Block diagonal representation; Structured block diagonal representation; ALGORITHM; SEGMENTATION; MODELS;
D O I
10.1007/s10489-020-01629-z
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The aim of the subspace clustering is to segment the high-dimensional data into the corresponding subspace. The structured sparse subspace clustering and the block diagonal representation clustering are quite advanced spectral-type subspace clustering algorithms when handling to the linear subspaces. In this paper, the respective advantages of these two algorithms are fully exploited, and the structured block diagonal representation (SBDR) subspace clustering is proposed. In many classical spectral-type subspace clustering algorithms, the affinity matrix which obeys the block diagonal property can not necessarily bring satisfying clustering results. However, thek-block diagonal regularizer of the SBDR algorithm directly pursues the block diagonal matrix, and this regularizer is obviously more effective. On the other hand, the general procedure of the spectral-type subspace clustering algorithm is to get the affinity matrix firstly and next perform the spectral clustering. The SBDR algorithm considers the intrinsic relationship of the two seemingly separate steps, the subspace structure matrix obtained by the spectral clustering is used iteratively to facilitate a better initialization for the representation matrix. The experimental results on the synthetic dataset and the real dataset have demonstrated the superior performance of the proposed algorithm over other prevalent subspace clustering algorithms.
引用
收藏
页码:2523 / 2536
页数:14
相关论文
共 45 条
[1]  
[Anonymous], 2011, ARXIV PREPRINT ARXIV
[2]   Lambertian reflectance and linear subspaces [J].
Basri, R ;
Jacobs, DW .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2003, 25 (02) :218-233
[3]   Structured Sparse Subspace Clustering with Within-Cluster Grouping [J].
Chen, Huazhu ;
Wang, Weiwei ;
Feng, Xiangchu .
PATTERN RECOGNITION, 2018, 83 :107-118
[4]   Discriminative and coherent subspace clustering [J].
Chen, Huazhu ;
Wang, Weiwei ;
Feng, Xiangchu ;
He, Ruiqiang .
NEUROCOMPUTING, 2018, 284 :177-186
[5]   Learning With l1-Graph for Image Analysis [J].
Cheng, Bin ;
Yang, Jianchao ;
Yan, Shuicheng ;
Fu, Yun ;
Huang, Thomas S. .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2010, 19 (04) :858-866
[6]   A multibody factorization method for independently moving objects [J].
Costeira, JP ;
Kanade, T .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 1998, 29 (03) :159-179
[7]  
Dattorro J., 2016, CONVEX OPTIMIZATION, P515
[8]   Low-rank local tangent space embedding for subspace clustering [J].
Deng, Tingquan ;
Ye, Dongsheng ;
Ma, Rong ;
Fujita, Hamido ;
Xiong, Lvnan .
INFORMATION SCIENCES, 2020, 508 :1-21
[9]   An Adaptive Density Data Stream Clustering Algorithm [J].
Ding, Shifei ;
Zhang, Jian ;
Jia, Hongjie ;
Qian, Jun .
COGNITIVE COMPUTATION, 2016, 8 (01) :30-38
[10]  
Dong W, 2018, NEURAL PROCESS LETT, P1