Multi-Scale Spectral-Spatial Attention Network for Hyperspectral Image Classification Combining 2D Octave and 3D Convolutional Neural Networks

被引:6
|
作者
Liang, Lianhui [1 ]
Zhang, Shaoquan [2 ]
Li, Jun [3 ]
Plaza, Antonio [4 ]
Cui, Zhi [1 ]
机构
[1] Hunan Univ, Coll Elect & Informat Engn, Changsha 418002, Peoples R China
[2] Nanchang Inst Technol, Sch Informat Engn, Jiangxi Prov Key Lab Water Informat Cooperat Sensi, Nanchang 330099, Peoples R China
[3] China Univ Geosci, Sch Comp Sci, Hubei Key Lab Intelligent Geoinformat Proc, Wuhan 430078, Peoples R China
[4] Univ Extremadura, Dept Technol Comp & Commun, Hyperspectral Comp Lab, E-10071 Caceres, Spain
关键词
hyperspectral images (HSIs); deep learning; convolutional neural networks (CNNs); 2D octave convolution; DenseNet; FUSION;
D O I
10.3390/rs15071758
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Traditional convolutional neural networks (CNNs) can be applied to obtain the spectral-spatial feature information from hyperspectral images (HSIs). However, they often introduce significant redundant spatial feature information. The octave convolution network is frequently utilized instead of traditional CNN to decrease spatial redundant information of the network and extend its receptive field. However, the 3D octave convolution-based approaches may introduce extensive parameters and complicate the network. To solve these issues, we propose a new HSI classification approach with a multi-scale spectral-spatial network-based framework that combines 2D octave and 3D CNNs. Our method, called MOCNN, first utilizes 2D octave convolution and 3D DenseNet branch networks with various convolutional kernel sizes to obtain complex spatial contextual feature information and spectral characteristics, separately. Moreover, the channel and the spectral attention mechanisms are, respectively, applied to these two branch networks to emphasize significant feature regions and certain important spectral bands that comprise discriminative information for the categorization. Furthermore, a sample balancing strategy is applied to address the sample imbalance problem. Expansive experiments are undertaken on four HSI datasets, demonstrating that our MOCNN approach outperforms several other methods for HSI classification, especially in scenarios dominated by limited and imbalanced sample data.
引用
收藏
页数:24
相关论文
共 50 条
  • [31] Spectral-spatial attention bilateral network for hyperspectral image classification
    Yang X.
    Chi Y.
    Zhou Y.
    Wang Y.
    National Remote Sensing Bulletin, 2023, 27 (11) : 2565 - 2578
  • [32] Residual Spectral-Spatial Attention Network for Hyperspectral Image Classification
    Zhu, Minghao
    Jiao, Licheng
    Liu, Fang
    Yang, Shuyuan
    Wang, Jianing
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2021, 59 (01): : 449 - 462
  • [33] Lightweight Spectral-Spatial Attention Network for Hyperspectral Image Classification
    Cui, Ying
    Xia, Jinbiao
    Wang, Zhiteng
    Gao, Shan
    Wang, Liguo
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2022, 60
  • [34] Expansion Spectral-Spatial Attention Network for Hyperspectral Image Classification
    Wang, Shuo
    Liu, Zhengjun
    Chen, Yiming
    Hou, Chengchao
    Liu, Aixia
    Zhang, Zhenbei
    IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2023, 16 : 6411 - 6427
  • [35] A novel spectral-spatial multi-scale network for hyperspectral image classification with the Res2Net block
    Zhang, Zhongqiang
    Liu, Danhua
    Gao, Dahua
    Shi, Guangming
    INTERNATIONAL JOURNAL OF REMOTE SENSING, 2022, 43 (03) : 751 - 777
  • [36] SPECTRAL-SPATIAL FUSED ATTENTION NETWORK FOR HYPERSPECTRAL IMAGE CLASSIFICATION
    Li, Ningyang
    Wang, Zhaohui
    2021 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2021, : 3832 - 3836
  • [37] Hierarchical Multi-Scale Convolutional Neural Networks for Hyperspectral Image Classification
    Li, Simin
    Zhu, Xueyu
    Bao, Jie
    SENSORS, 2019, 19 (07)
  • [38] Multi-Scale Dilated Convolutional Neural Network for Hyperspectral Image Classification
    Shanshan Zheng
    Wen Liu
    Rui Shan
    Jingyi Zhao
    Guoqian Jiang
    Zhi Zhang
    Journal of Harbin Institute of Technology(New series), 2021, 28 (04) : 25 - 32
  • [39] Deep Multi-scale Convolutional Neural Network for Hyperspectral Image Classification
    Zhang Feng-zhe
    Yang Xia
    NINTH INTERNATIONAL CONFERENCE ON GRAPHIC AND IMAGE PROCESSING (ICGIP 2017), 2018, 10615
  • [40] HYPERSPECTRAL IMAGE SUPER-RESOLUTION BASED ON MULTI-SCALE WAVELET 3D CONVOLUTIONAL NEURAL NETWORK
    Yang, Jingxiang
    Zhao, Yong-Qiang
    Chan, Jonathan Cheung-Wai
    2019 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2019), 2019, : 2770 - 2773