An Unsupervised Band Selection Method via Contrastive Learning for Hyperspectral Images

被引:1
|
作者
Li, Xiaorun [1 ]
Liu, Yufei [1 ]
Hua, Ziqiang [1 ]
Chen, Shuhan [1 ]
机构
[1] Zhejiang Univ, Coll Elect Engn, Hangzhou 310027, Peoples R China
关键词
unsupervised band selection; contrastive learning; hyperspectral image; attention mechanism;
D O I
10.3390/rs15235495
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Band selection (BS) is an efficacious approach to reduce hyperspectral information redundancy while preserving the physical meaning of hyperspectral images (HSIs). Recently, deep learning-based BS methods have received widespread interest due to their ability to model the nonlinear relationship between bands, with existing methods typically relying on generative algorithms. However, the process of generating images with pixel-level detail required by generative algorithm-based BS methods is computationally expensive. To alleviate this issue, we propose a contrastive learning-based unsupervised BS architecture, termed ContrastBS, in this article. With the help of contrastive learning, the proposed architecture avoids the costly generation step in pixel space by learning to distinguish data at the abstract semantic level of the feature space. Specifically, ContrastBS combines an attention mechanism with contrastive learning to extract the importance of each band. Furthermore, we design a novel loss function, which is able to constrain the symmetric loss while ensuring attention to the most valuable bands, for the contrastive learning-based BS network. Experimental results indicate that ContrastBS has excellent classification performance and competitive time cost compared to the comparison methods.
引用
收藏
页数:17
相关论文
共 50 条
  • [11] Unsupervised Hyperspectral Band Selection via Hybrid Graph Convolutional Network
    Yu, Chunyan
    Zhou, Sijia
    Song, Meiping
    Gong, Baoyu
    Zhao, Enyu
    Chang, Chein-, I
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2022, 60
  • [12] A New Unsupervised Hyperspectral Band Selection Method Based on Multiobjective Optimization
    Xu, Xia
    Shi, Zhenwei
    Pan, Bin
    IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2017, 14 (11) : 2112 - 2116
  • [13] Unsupervised band selection for hyperspectral image analysis
    Du, Qian
    Yang, He
    IGARSS: 2007 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, VOLS 1-12: SENSING AND UNDERSTANDING OUR PLANET, 2007, : 282 - 285
  • [14] An unsupervised algorithm for the selection of endmembers in hyperspectral images
    Acito, N
    Corsini, G
    Diani, M
    IGARSS 2002: IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM AND 24TH CANADIAN SYMPOSIUM ON REMOTE SENSING, VOLS I-VI, PROCEEDINGS: REMOTE SENSING: INTEGRATING OUR VIEW OF THE PLANET, 2002, : 1673 - 1675
  • [15] Unsupervised Hyperspectral Band Selection via Multimodal Evolutionary Algorithm and Subspace Decomposition
    Wei, Yunpeng
    Hu, Huiqiang
    Xu, Huaxing
    Mao, Xiaobo
    SENSORS, 2023, 23 (04)
  • [16] Robust Unsupervised Hyperspectral Band Selection via Global Affinity Matrix Reconstruction
    You, Mengbo
    Yuan, Aihong
    Zou, Min
    Konno, Kouichi
    IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2023, 16 : 7374 - 7384
  • [17] Structural graph learning method for hyperspectral band selection
    Li, Shuying
    Liu, Zhe
    Fang, Long
    Li, Qiang
    INTERNATIONAL JOURNAL OF REMOTE SENSING, 2024, 45 (18) : 6719 - 6743
  • [18] A Binary Social Spider Optimization algorithm for unsupervised band selection in compressed hyperspectral images
    Shukla, Urvashi Prakash
    Nanda, Satyasai Jagannath
    EXPERT SYSTEMS WITH APPLICATIONS, 2018, 97 : 336 - 356
  • [19] Unsupervised band selection of medical hyperspectral images guided by data gravitation and weak correlation
    Zhang, Chenglong
    Zhang, Zhimin
    Yu, Dexin
    Cheng, Qiyuan
    Shan, Shihao
    Li, Mengjiao
    Mou, Lichao
    Yang, Xiaoli
    Ma, Xiaopeng
    COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, 2023, 240
  • [20] Extending Contrastive Learning to Unsupervised Coreset Selection
    Ju, Jeongwoo
    Jung, Heechul
    Oh, Yoonju
    Kim, Junmo
    IEEE ACCESS, 2022, 10 : 7704 - 7715