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

被引:7
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] Res2Net with spectral-spatial and channel attention for hyperspectral image classification
    Xu, Qin
    Xu, Shumeng
    Wang, Dongyue
    Yang, Chao
    Liu, Jinpei
    Luo, Bin
    JOURNAL OF INTELLIGENT & FUZZY SYSTEMS, 2022, 43 (05) : 6765 - 6781
  • [32] MSAC-Net: 3D Multi-Scale Attention Convolutional Network for Multi-Spectral Imagery Pansharpening
    Zhang, Erlei
    Fu, Yihao
    Wang, Jun
    Liu, Lu
    Yu, Kai
    Peng, Jinye
    REMOTE SENSING, 2022, 14 (12)
  • [33] Dimensionality-varied convolutional neural network for spectral-spatial classification of hyperspectral data
    Liu, Wanjun
    Liang, Xuejian
    Qu, Haicheng
    LIDAR IMAGING DETECTION AND TARGET RECOGNITION 2017, 2017, 10605
  • [34] Dual-stream spectral-spatial convolutional neural network for hyperspectral image classification and optimal band selection
    Atik, Saziye Ozge
    ADVANCES IN SPACE RESEARCH, 2024, 74 (05) : 2025 - 2041
  • [35] Hyperspectral image classification using spectral-spatial hypergraph convolution neural network
    Ma, Zhongtian
    Jiang, Zhiguo
    Zhang, Haopeng
    IMAGE AND SIGNAL PROCESSING FOR REMOTE SENSING XXVII, 2021, 11862
  • [36] Mixed 2D/3D Convolutional Network for Hyperspectral Image Super-Resolution
    Li, Qiang
    Wang, Qi
    Li, Xuelong
    REMOTE SENSING, 2020, 12 (10)
  • [37] Hyperspectral Image Classification Using a Hybrid 3D-2D Convolutional Neural Networks
    Ghaderizadeh, Saeed
    Abbasi-Moghadam, Dariush
    Sharifi, Alireza
    Zhao, Na
    Tariq, Aqil
    IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2021, 14 (14) : 7570 - 7588
  • [38] 3-D Gabor Convolutional Neural Network for Hyperspectral Image Classification
    Jia, Sen
    Liao, Jianhui
    Xu, Meng
    Li, Yan
    Zhu, Jiasong
    Sun, Weiwei
    Jia, Xiuping
    Li, Qingquan
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2022, 60
  • [39] 3D Convolutional Neural Networks Initialized from Pretrained 2D Convolutional Neural Networks for Classification of Industrial Parts
    Merino, Ibon
    Azpiazu, Jon
    Remazeilles, Anthony
    Sierra, Basilio
    SENSORS, 2021, 21 (04) : 1 - 18
  • [40] Deep Multi-Scale 3D Convolutional Neural Network (CNN) for MRI Gliomas Brain Tumor Classification
    Mzoughi, Hiba
    Njeh, Ines
    Wali, Ali
    Ben Slima, Mohamed
    BenHamida, Ahmed
    Mhiri, Chokri
    Ben Mahfoudhe, Kharedine
    JOURNAL OF DIGITAL IMAGING, 2020, 33 (04) : 903 - 915