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
  • [1] Spectral-Spatial Classification of Hyperspectral Imagery with 3D Convolutional Neural Network
    Li, Ying
    Zhang, Haokui
    Shen, Qiang
    REMOTE SENSING, 2017, 9 (01)
  • [2] MULTI-SCALE 3D DEEP CONVOLUTIONAL NEURAL NETWORK FOR HYPERSPECTRAL IMAGE CLASSIFICATION
    He, Mingyi
    Li, Bo
    Chen, Huahui
    2017 24TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2017, : 3904 - 3908
  • [3] A 3D Cascaded Spectral-Spatial Element Attention Network for Hyperspectral Image Classification
    Yan, Huaiping
    Wang, Jun
    Tang, Lei
    Zhang, Erlei
    Yan, Kun
    Yu, Kai
    Peng, Jinye
    REMOTE SENSING, 2021, 13 (13)
  • [4] MS3A-Net: multi-scale and spectral-spatial attention network for hyperspectral image classification
    Dai, Mengyun
    Sun, Qi
    Dai, Luanyan
    Lin, Yaohai
    Wei, Lifang
    Yang, Changcai
    Chen, Riqing
    INTERNATIONAL JOURNAL OF REMOTE SENSING, 2022, 43 (19-24) : 7139 - 7160
  • [5] 3D Octave and 2D Vanilla Mixed Convolutional Neural Network for Hyperspectral Image Classification with Limited Samples
    Feng, Yuchao
    Zheng, Jianwei
    Qin, Mengjie
    Bai, Cong
    Zhang, Jinglin
    REMOTE SENSING, 2021, 13 (21)
  • [6] A lightweight 3D-2D convolutional neural network for spectral-spatial classification of hyperspectral images
    Haque, Md Rakibul
    Mishu, Sadia Zaman
    Uddin, Md Palash
    Al Mamun, Md
    JOURNAL OF INTELLIGENT & FUZZY SYSTEMS, 2022, 43 (01) : 1241 - 1258
  • [7] Synergistic 2D/3D Convolutional Neural Network for Hyperspectral Image Classification
    Yang, Xiaofei
    Zhang, Xiaofeng
    Ye, Yunming
    K Lau, Raymond Y.
    Lu, Shijian
    Li, Xutao
    Huang, Xiaohui
    REMOTE SENSING, 2020, 12 (12)
  • [8] A Novel 2D-3D CNN with Spectral-Spatial Multi-Scale Feature Fusion for Hyperspectral Image Classification
    Liu, Dongxu
    Han, Guangliang
    Liu, Peixun
    Yang, Hang
    Sun, Xinglong
    Li, Qingqing
    Wu, Jiajia
    REMOTE SENSING, 2021, 13 (22)
  • [9] A Spectral-Spatial Cascaded 3D Convolutional Neural Network with a Convolutional Long Short-Term Memory Network for Hyperspectral Image Classification
    Qi, Wenchao
    Zhang, Xia
    Wang, Nan
    Zhang, Mao
    Cen, Yi
    REMOTE SENSING, 2019, 11 (20)
  • [10] SPECTRAL-SPATIAL CLASSIFICATION OF HYPERSPECTRAL DATA USING 3D-2D CONVOLUTIONAL NEURAL NETWORK AND INCEPTION NETWORK
    Nyabuga, Douglas Omwenga
    Li, Guohua
    IADIS-INTERNATIONAL JOURNAL ON COMPUTER SCIENCE AND INFORMATION SYSTEMS, 2021, 16 (02): : 29 - 44