Robust Tensor Analysis With L1-Norm

被引:163
|
作者
Pang, Yanwei [1 ]
Li, Xuelong [2 ]
Yuan, Yuan [3 ]
机构
[1] Tianjin Univ, Sch Elect Informat Engn, Tianjin 300072, Peoples R China
[2] Chinese Acad Sci, State Key Lab Transient Opt & Photon, Xian Inst Opt & Precis Mech, Xian 710119, Peoples R China
[3] Aston Univ, Sch Engn & Appl Sci, Birmingham B4 7ET, W Midlands, England
基金
中国国家自然科学基金;
关键词
L1-norm; outlier; tensor analysis; APPEARANCE;
D O I
10.1109/TCSVT.2009.2020337
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Tensor analysis plays an important role in modern image and vision computing problems. Most of the existing tensor analysis approaches are based on the Frobenius norm, which makes them sensitive to outliers. In this paper, we propose L1-norm-based tensor analysis (TPCA-L1), which is robust to outliers. Experimental results upon face and other datasets demonstrate the advantages of the proposed approach.
引用
收藏
页码:172 / 178
页数:7
相关论文
共 50 条
  • [41] MONOSPLINES OF MINIMAL L1-NORM
    ZHENSYKBAEV, AA
    MATHEMATICAL NOTES, 1983, 33 (5-6) : 443 - 452
  • [42] The L1-Norm of a Trigonometric Sum
    K. M. Éminyan
    Mathematical Notes, 2004, 76 : 124 - 132
  • [43] Robust sequential subspace clustering via l1-norm temporal graph
    Hu, Wenyu
    Li, Shenghao
    Zheng, Weidong
    Lu, Yao
    Yu, Gaohang
    NEUROCOMPUTING, 2020, 383 : 380 - 395
  • [44] On the concentration of measure and the L1-norm
    Malykhin, Yu. V.
    Ryutin, K. S.
    JOURNAL OF APPROXIMATION THEORY, 2013, 175 : 77 - 82
  • [45] ROBUST NONPARAMETRIC REGRESSION BASED ON L1-NORM AND B-SPLINES
    SHI Peide(Department of Probability and Statistics
    Journal of Systems Science & Complexity, 1995, (02) : 187 - 192
  • [46] 2DPCA with L1-norm for simultaneously robust and sparse modelling
    Wang, Haixian
    Wang, Jing
    NEURAL NETWORKS, 2013, 46 : 190 - 198
  • [47] A Novel Robust Image Forensics Algorithm Based on L1-Norm Estimation
    He, Xin
    Guan, Qingxiao
    Tong, Yanfei
    Zhao, Xianfeng
    Yu, Haibo
    DIGITAL FORENSICS AND WATERMARKING, IWDW 2016, 2017, 10082 : 145 - 158
  • [48] Robust Decomposition of 3-way Tensors based on L1-norm
    Chachlakis, Dimitris G.
    Markopoulos, Panos P.
    COMPRESSIVE SENSING VII: FROM DIVERSE MODALITIES TO BIG DATA ANALYTICS, 2018, 10658
  • [49] High-dimensional inference robust to outliers with l1-norm penalization
    Beyhum, Jad
    COMMUNICATIONS IN STATISTICS-THEORY AND METHODS, 2023, 52 (16) : 5866 - 5876
  • [50] Linear Discriminant Analysis Based on L1-Norm Maximization
    Zhong, Fujin
    Zhang, Jiashu
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2013, 22 (08) : 3018 - 3027