Locality-Constrained Low-Rank Coding for Image Classification

被引:0
|
作者
Jiang, Ziheng [1 ]
Guo, Ping [1 ]
Peng, Lihong [2 ]
机构
[1] Beijing Inst Technol, Sch Comp Sci & Technol, Beijing 100081, Peoples R China
[2] Natl Univ Def Technol, Sch Comp Sci, Changsha 410073, Hunan, Peoples R China
基金
北京市自然科学基金; 中国国家自然科学基金;
关键词
SPARSE; RECOVERY;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Low-rank coding (LRC), originated from matrix decomposition, is recently introduced into image classification. Following the standard bag-of-words (BOW) pipeline, when coding the data matrix in the sense of low-rankness incorporates contextual information into the traditional BOW model, this can capture the dependency relationship among neighbor patches. It differs from the traditional sparse coding paradigms which encode patches independently. Current LRC-based methods use l(1) norm to increase the discrimination and sparseness of the learned codes. However, such methods fail to consider the local manifold structure between data space and dictionary space. To solve this problem, we propose a locality-constrained low-rank coding (LCLR) algorithm for image representations. By using the geometric structure information as a regularization term, we can obtain more discriminative representations. In addition, we present a fast and stable online algorithm to solve the optimization problem. In the experiments, we evaluate LCLR with four benchmarks, including one face recognition dataset (extended Yale B), one handwritten digit recognition dataset (USPS), and two image datasets (Scene13 for scene recognition and Caltech101 for object recognition). Experimental results show that our approach outperforms many state-of-the-art algorithms even with a linear classifier.
引用
收藏
页码:2780 / 2786
页数:7
相关论文
共 50 条
  • [1] Fast Locality-constrained Low-rank Coding for Image Classification
    Fan Min
    Wang Fen
    Wang Kai
    Shi Xin
    Liu Zhihong
    [J]. 2015 CHINESE AUTOMATION CONGRESS (CAC), 2015, : 644 - 650
  • [2] Locality-constrained Linear Coding for Image Classification
    Wang, Jinjun
    Yang, Jianchao
    Yu, Kai
    Lv, Fengjun
    Huang, Thomas
    Gong, Yihong
    [J]. 2010 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2010, : 3360 - 3367
  • [3] Locality-constrained Low Rank Coding for Face Recognition
    Arpit, Devansh
    Srivastava, Gaurav
    Fu, Yun
    [J]. 2012 21ST INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR 2012), 2012, : 1687 - 1690
  • [4] LOCALITY CONSTRAINED LOW-RANK REPRESENTATION FOR HYPERSPECTRAL IMAGE CLASSIFICATION
    Pan, Lei
    Li, Heng-Chao
    Chen, Xiang-Dong
    [J]. 2016 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS), 2016, : 493 - 496
  • [5] Laplacian regularized locality-constrained coding for image classification
    Min, Huaqing
    Liang, Mingjie
    Luo, Ronghua
    Zhu, Jinhui
    [J]. NEUROCOMPUTING, 2016, 171 : 1486 - 1495
  • [6] FACE HALLUCINATION VIA LOCALITY-CONSTRAINED LOW-RANK REPRESENTATION
    Lu, Tao
    Xiong, Zixiang
    Wan, Yongjing
    Yang, Wei
    [J]. 2016 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING PROCEEDINGS, 2016, : 1746 - 1750
  • [7] A Dual Locality-Constrained Linear Coding Algorithm for Image Classification
    Wang, Xianchen
    Li, Yanshan
    Xie, Weixin
    [J]. IEEE ACCESS, 2018, 6 : 19247 - 19254
  • [8] CSIFT based locality-constrained linear coding for image classification
    Chen, Junzhou
    Li, Qing
    Peng, Qiang
    Wong, Kin Hong
    [J]. PATTERN ANALYSIS AND APPLICATIONS, 2015, 18 (02) : 441 - 450
  • [9] Locality-constrained affine subspace coding for image classification and retrieval
    Zhang, Bingbing
    Wang, Qilong
    Lu, Xiaoxiao
    Wang, Fasheng
    Li, Peihua
    [J]. PATTERN RECOGNITION, 2020, 100 (100)
  • [10] CSIFT based locality-constrained linear coding for image classification
    Junzhou Chen
    Qing Li
    Qiang Peng
    Kin Hong Wong
    [J]. Pattern Analysis and Applications, 2015, 18 : 441 - 450