Hyperspectral Image Classification Based on A Multi-Scale Weighted Kernel Network

被引:5
作者
Sun Le [1 ,3 ]
Xu Bin [2 ]
Lu Zhenyu [2 ]
机构
[1] Nanjing Univ Informat Sci & Technol, Sch Comp Sci, Nanjing 210044, Peoples R China
[2] Nanjing Univ Informat Sci & Technol, Sch Artificial Intelligence, Nanjing 210044, Peoples R China
[3] Nanjing Univ Informat Sci & Technol, Engn Res Ctr Digital Forens, Minist Educ, Nanjing 210044, Peoples R China
基金
中国国家自然科学基金;
关键词
Hyperspectral image classification; Convolutional neural network; Kernel network; Multi-scale features; Attention mechanism; RESIDUAL NETWORK; CNN;
D O I
10.1049/cje.2021.00.130
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Recently, many deep learning models have shown excellent performance in hyperspectral image (HSI) classification. Among them, networks with multiple convolution kernels of different sizes have been proved to achieve richer receptive fields and extract more representative features than those with a single convolution kernel. However, in most networks, different-sized convolution kernels are usually used directly on multi-branch structures, and the image features extracted from them are fused directly and simply. In this paper, to fully and adaptively explore the multiscale information in both spectral and spatial domains of HSI, a novel multi-scale weighted kernel network (MSWKNet) based on an adaptive receptive field is proposed. First, the original HSI cubic patches are transformed to the input features by combining the principal component analysis and one-dimensional spectral convolution. Then, a three-branch network with different convolution kernels is designed to convolve the input features, and adaptively adjust the size of the receptive field through the attention mechanism of each branch. Finally, the features extracted from each branch are fused together for the task of classification. Experiments on three well-known hyperspectral data sets show that MSWKNet outperforms many deep learning networks in HSI classification.
引用
收藏
页码:832 / 843
页数:12
相关论文
共 45 条
[1]  
[Anonymous], 2015, ICLR
[2]   3-D Deep Learning Approach for Remote Sensing Image Classification [J].
Ben Hamida, Amina ;
Benoit, Alexandre ;
Lambert, Patrick ;
Ben Amar, Chokri .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2018, 56 (08) :4420-4434
[3]  
Bidari I, 2020, PROCEEDINGS OF THE 2020 FOURTH WORLD CONFERENCE ON SMART TRENDS IN SYSTEMS, SECURITY AND SUSTAINABILITY (WORLDS4 2020), P672, DOI [10.1109/WorldS450073.2020.9210332, 10.1109/worlds450073.2020.9210332]
[4]   Composite kernels for hyperspectral image classification [J].
Camps-Valls, G ;
Gomez-Chova, L ;
Muñoz-Marí, J ;
Vila-Francés, J ;
Calpe-Maravilla, J .
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2006, 3 (01) :93-97
[5]   Semisupervised Feature Extraction of Hyperspectral Image Using Nonlinear Geodesic Sparse Hypergraphs [J].
Duan, Yule ;
Huang, Hong ;
Wang, Tao .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2022, 60
[6]   Learning Robust Discriminant Subspace Based on Joint L2, p- and L2,s-Norm Distance Metrics [J].
Fu, Liyong ;
Li, Zechao ;
Ye, Qiaolin ;
Yin, Hang ;
Liu, Qingwang ;
Chen, Xiaobo ;
Fan, Xijian ;
Yang, Wankou ;
Yang, Guowei .
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2022, 33 (01) :130-144
[7]   Influence of the receptive field size on accuracy and performance of a convolutional neural network [J].
Gabbasov, Rail ;
Paringer, Rustam .
2020 VI INTERNATIONAL CONFERENCE ON INFORMATION TECHNOLOGY AND NANOTECHNOLOGY (IEEE ITNT-2020), 2020,
[8]   A CNN With Multiscale Convolution and Diversified Metric for Hyperspectral Image Classification [J].
Gong, Zhiqiang ;
Zhong, Ping ;
Yu, Yang ;
Hu, Weidong ;
Li, Shutao .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2019, 57 (06) :3599-3618
[9]   A CNN-Based Spatial Feature Fusion Algorithm for Hyperspectral Imagery Classification [J].
Guo, Alan J. X. ;
Zhu, Fei .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2019, 57 (09) :7170-7181
[10]   Visual Attention-Driven Hyperspectral Image Classification [J].
Haut, Juan Mario ;
Paoletti, Mercedes E. ;
Plaza, Javier ;
Plaza, Antonio ;
Li, Jun .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2019, 57 (10) :8065-8080