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
  • [1] Multi-Objective Unsupervised Band Selection Method for Hyperspectral Images Classification
    Ou, Xianfeng
    Wu, Meng
    Tu, Bing
    Zhang, Guoyun
    Li, Wujing
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2023, 32 : 1952 - 1965
  • [2] Unsupervised Band Selection of Hyperspectral Images via Multi-Dictionary Sparse Representation
    Li, Fei
    Zhang, Pingping
    Lu, Huchuan
    IEEE ACCESS, 2018, 6 : 71632 - 71643
  • [3] AN UNSUPERVISED BAND SELECTION METHOD FOR HYPERSPECTRAL IMAGES USING MUTUAL INFORMATION BASED DEPENDENCE INDEX
    Jain, Namita
    Ghosh, Susmita
    2022 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2022), 2022, : 783 - 786
  • [4] Unsupervised Hyperspectral Band Selection via Multimodal Evolutionary Algorithm and Subspace Decomposition
    Wei, Yunpeng
    Hu, Huiqiang
    Xu, Huaxing
    Mao, Xiaobo
    SENSORS, 2023, 23 (04)
  • [5] Combination of Clustering and Ranking Techniques for Unsupervised Band Selection of Hyperspectral Images
    Datta, Aloke
    Ghosh, Susmita
    Ghosh, Ashish
    IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2015, 8 (06) : 2814 - 2823
  • [6] Unsupervised Band Selection Based on Evolutionary Multiobjective Optimization for Hyperspectral Images
    Gong, Maoguo
    Zhang, Mingyang
    Yuan, Yuan
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2016, 54 (01): : 544 - 557
  • [7] Unsupervised Discriminative Feature Selection via Contrastive Graph Learning
    Zhou, Qian
    Wang, Qianqian
    Gao, Quanxue
    Yang, Ming
    Gao, Xinbo
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2024, 33 : 972 - 986
  • [8] Novel hyperbolic clustering-based band hierarchy (HCBH) for effective unsupervised band selection of hyperspectral images
    Sun, He
    Zhang, Lei
    Ren, Jinchang
    Huang, Hua
    PATTERN RECOGNITION, 2022, 130
  • [9] Extending Contrastive Learning to Unsupervised Coreset Selection
    Ju, Jeongwoo
    Jung, Heechul
    Oh, Yoonju
    Kim, Junmo
    IEEE ACCESS, 2022, 10 : 7704 - 7715
  • [10] ANOMALY DETECTION IN HYPERSPECTRAL IMAGES VIA SUPERPIXEL SEGMENTATION AND UNSUPERVISED BACKGROUND LEARNING
    Arisoy, Sertac
    Kayabol, Koray
    2019 10TH WORKSHOP ON HYPERSPECTRAL IMAGING AND SIGNAL PROCESSING - EVOLUTION IN REMOTE SENSING (WHISPERS), 2019,