Unified Framework for Faster Clustering via Joint Schatten p-Norm Factorization With Optimal Mean

被引:8
作者
Zhang, Hengmin [1 ,2 ]
Zhao, Jiaoyan [3 ]
Zhang, Bob [1 ,2 ]
Gong, Chen [4 ]
Qian, Jianjun [4 ]
Yang, Jian [4 ]
机构
[1] Univ Macau, Inst Collaborat Innovat, Dept Comp & Informat Sci, PAMI Res Grp, Macau, Peoples R China
[2] Univ Macau, Inst Collaborat Innovat, Ctr Artificial Intelligence & Robot, Macau, Peoples R China
[3] Shenzhen Polytech Univ, Sch Artificial Intelligence, Shenzhen 518055, Peoples R China
[4] Nanjing Univ Sci & Technol, Sch Comp Sci & Engn, Key Lab Intelligent Percept & Syst & High Dimens I, PCA Lab,Minist Educ, Nanjing 210094, Peoples R China
基金
中国博士后科学基金;
关键词
Optimization; Computational complexity; Clustering algorithms; Minimization; Convergence; Computational modeling; Learning systems; Low-rank representation (LRR); matrix factorization; optimal mean; Schatten p-norm; subspace clustering; MATRIX COMPLETION; RANK; NONCONVEX; SUBSPACE; MINIMIZATION; ALGORITHM; CONVERGENCE;
D O I
10.1109/TNNLS.2023.3327716
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
To enhance the effectiveness and efficiency of subspace clustering in visual tasks, this work introduces a novel approach that automatically eliminates the optimal mean, which is embedded in the subspace clustering framework of low-rank representation (LRR) methods, along with the computationally factored formulation of Schatten p-norm. By addressing the issues related to meaningful computations involved in some LRR methods and overcoming biased estimation of the low-rank solver, we propose faster nonconvex subspace clustering methods through joint Schatten p-norm factorization with optimal mean (JSpNFOM), forming a unified framework for enhancing performance while reducing time consumption. The proposed approach employs tractable and scalable factor techniques, which effectively address the disadvantages of higher computational complexity, particularly when dealing with large-scale coefficient matrices. The resulting nonconvex minimization problems are reformulated and further iteratively optimized by multivariate weighting algorithms, eliminating the need for singular value decomposition (SVD) computations in the developed iteration procedures. Moreover, each subproblem can be guaranteed to obtain the closed-form solver, respectively. The theoretical analyses of convergence properties and computational complexity further support the applicability of the proposed methods in real-world scenarios. Finally, comprehensive experimental results demonstrate the effectiveness and efficiency of the proposed nonconvex clustering approaches compared to existing state-of-the-art methods on several publicly available databases. The demonstrated improvements highlight the practical significance of our work in subspace clustering tasks for visual data analysis. The source code for the proposed algorithms is publicly accessible at https://github.com/ZhangHengMin/TRANSUFFC.
引用
收藏
页码:3012 / 3026
页数:15
相关论文
共 64 条
[21]  
Kim E, 2015, PROC CVPR IEEE, P915, DOI 10.1109/CVPR.2015.7298693
[22]   Joint Sparse Representation and Robust Feature-Level Fusion for Multi-Cue Visual Tracking [J].
Lan, Xiangyuan ;
Ma, Andy J. ;
Yuen, Pong C. ;
Chellappa, Rama .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2015, 24 (12) :5826-5841
[23]   Robust kernel principal component analysis with optimal mean [J].
Li, Pei ;
Zhang, Wenlin ;
Lu, Chengjun ;
Zhang, Rui ;
Li, Xuelong .
NEURAL NETWORKS, 2022, 152 :347-352
[24]  
Lin J, 2021, ADV NEUR IN, V34
[25]   ON THE GLOBAL LINEAR CONVERGENCE OF THE ADMM WITH MULTIBLOCK VARIABLES [J].
Lin, Tianyi ;
Ma, Shiqian ;
Zhang, Shuzhong .
SIAM JOURNAL ON OPTIMIZATION, 2015, 25 (03) :1478-1497
[26]  
Lin Z., 2011, NIPS, P612
[27]   Robust Recovery of Subspace Structures by Low-Rank Representation [J].
Liu, Guangcan ;
Lin, Zhouchen ;
Yan, Shuicheng ;
Sun, Ju ;
Yu, Yong ;
Ma, Yi .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2013, 35 (01) :171-184
[28]   Active Subspace: Toward Scalable Low-Rank Learning [J].
Liu, Guangcan ;
Yan, Shuicheng .
NEURAL COMPUTATION, 2012, 24 (12) :3371-3394
[29]  
Liu GC, 2011, IEEE I CONF COMP VIS, P1615, DOI 10.1109/ICCV.2011.6126422
[30]   Nonconvex Nonsmooth Low Rank Minimization via Iteratively Reweighted Nuclear Norm [J].
Lu, Canyi ;
Tang, Jinhui ;
Yan, Shuicheng ;
Lin, Zhouchen .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2016, 25 (02) :829-839