Kernel Joint Sparse Representation Based on Self-Paced Learning for Hyperspectral Image Classification

被引:5
|
作者
Hu, Sixiu [1 ]
Peng, Jiangtao [1 ]
Fu, Yingxiong [1 ]
Li, Luoqing [1 ]
机构
[1] Hubei Univ, Fac Math & Stat, Hubei Key Lab Appl Math, Wuhan 430062, Hubei, Peoples R China
基金
中国国家自然科学基金;
关键词
hyperspectral image classification; self-paced learning; kernel; joint sparse representation; SPATIAL CLASSIFICATION;
D O I
10.3390/rs11091114
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
By means of joint sparse representation (JSR) and kernel representation, kernel joint sparse representation (KJSR) models can effectively model the intrinsic nonlinear relations of hyperspectral data and better exploit spatial neighborhood structure to improve the classification performance of hyperspectral images. However, due to the presence of noisy or inhomogeneous pixels around the central testing pixel in the spatial domain, the performance of KJSR is greatly affected. Motivated by the idea of self-paced learning (SPL), this paper proposes a self-paced KJSR (SPKJSR) model to adaptively learn weights and sparse coefficient vectors for different neighboring pixels in the kernel-based feature space. SPL strateges can learn a weight to indicate the difficulty of feature pixels within a spatial neighborhood. By assigning small weights for unimportant or complex pixels, the negative effect of inhomogeneous or noisy neighboring pixels can be suppressed. Hence, SPKJSR is usually much more robust. Experimental results on Indian Pines and Salinas hyperspectral data sets demonstrate that SPKJSR is much more effective than traditional JSR and KJSR models.
引用
收藏
页数:18
相关论文
共 50 条
  • [21] Pyramidal Dilation Attention Convolutional Network With Active and Self-Paced Learning for Hyperspectral Image Classification
    Hou, Wenhui
    Chen, Na
    Peng, Jiangtao
    Sun, Weiwei
    Du, Qian
    IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2023, 16 : 1503 - 1518
  • [22] Use of customizing kernel sparse representation for hyperspectral image classification
    Qi, Bin
    Zhao, Chunhui
    Yin, Guisheng
    APPLIED OPTICS, 2015, 54 (04) : 707 - 716
  • [23] SEA ICE CLASSIFICATION FROM HYPERSPECTRAL IMAGES BASED ON SELF-PACED BOOST LEARNING
    Wang, Dong
    Gao, Feng
    Dong, Junyu
    Yang, Yang
    Wang, Shengke
    IGARSS 2018 - 2018 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, 2018, : 7324 - 7327
  • [24] Leveraging self-paced learning and deep sparse embedding for image clustering
    Yanming Liu
    Jinglei Liu
    Neural Computing and Applications, 2024, 36 : 5135 - 5151
  • [25] Leveraging self-paced learning and deep sparse embedding for image clustering
    Liu, Yanming
    Liu, Jinglei
    NEURAL COMPUTING & APPLICATIONS, 2023, 36 (10): : 5135 - 5151
  • [26] Multi-modal self-paced learning for image classification
    Xu, Wei
    Liu, Wei
    Huang, Xiaolin
    Yang, Jie
    Qiu, Song
    NEUROCOMPUTING, 2018, 309 : 134 - 144
  • [27] Kernel Weighted Joint Collaborative Representation for Hyperspectral Image Classification
    Du, Qian
    Li, Wei
    SATELLITE DATA COMPRESSION, COMMUNICATIONS, AND PROCESSING XI, 2015, 9501
  • [28] CORRENTROPY-BASED ROBUST JOINT SPARSE REPRESENTATION FOR HYPERSPECTRAL IMAGE CLASSIFICATION
    Peng, Jiangtao
    Zhang, Lefei
    2016 8TH WORKSHOP ON HYPERSPECTRAL IMAGE AND SIGNAL PROCESSING: EVOLUTION IN REMOTE SENSING (WHISPERS), 2016,
  • [29] Fast Multifeature Joint Sparse Representation for Hyperspectral Image Classification
    Zhang, Erlei
    Zhang, Xiangrong
    Liu, Hongying
    Jiao, Licheng
    IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2015, 12 (07) : 1397 - 1401
  • [30] Nuclear Norm Joint Sparse Representation for Hyperspectral Image Classification
    Tao, Yingshan
    Yuan, Haoliang
    Lai, Loi Lei
    2017 CHINESE AUTOMATION CONGRESS (CAC), 2017, : 5443 - 5447