Multi-Branch Hybrid Network Based on Adaptive Selection of Spatial-Spectral Kernel for Hyperspectral Image Classification
The current limited sample set and mixed spatial-spectral information make effective feature extraction in hyperspectral image (HSI) classification challenging. To better extract spatial-spectral features, enhance the robustness of the learned features against the orientation and scale changes and i...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10198228/ |
| _version_ | 1797752048253403136 |
|---|---|
| author | Cailing Wang He Fu Hongwei Wang |
| author_facet | Cailing Wang He Fu Hongwei Wang |
| author_sort | Cailing Wang |
| collection | DOAJ |
| description | The current limited sample set and mixed spatial-spectral information make effective feature extraction in hyperspectral image (HSI) classification challenging. To better extract spatial-spectral features, enhance the robustness of the learned features against the orientation and scale changes and improve the convergence of the network used for HSI classification, we propose a multi-branch hybrid network (MHNet) based on adaptive selection of spatial-spectral kernels in this paper. Specifically, we use the Gabor convolutional layer as the first layer of this network model. Since the predefined multi-scale and multi-directional Gabor filters in this layer can better characterize the internal spatial-spectral structure of HSI data from different perspectives, the robustness of the model to orientation-scale changes is enhanced. Then the performance of joint spatial-spectral feature extraction is improved by learning adaptive selective 3D convolution kernels. Subsequently, a two-branch network is employed to further fully extract spatial and spectral information for classification accuracy. Experimental results on three public hyperspectral datasets show that the proposed MHNet not only has better classification performance than several existing widely used machine learning and deep learning-based methods, but also it has fast model convergence. |
| first_indexed | 2024-03-12T16:57:52Z |
| format | Article |
| id | doaj.art-8b991f5fdfe94d3f89ea1171432cd0b1 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-12T16:57:52Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-8b991f5fdfe94d3f89ea1171432cd0b12023-08-07T23:00:30ZengIEEEIEEE Access2169-35362023-01-0111805038051710.1109/ACCESS.2023.330042210198228Multi-Branch Hybrid Network Based on Adaptive Selection of Spatial-Spectral Kernel for Hyperspectral Image ClassificationCailing Wang0https://orcid.org/0000-0002-3455-8649He Fu1https://orcid.org/0009-0007-7239-9048Hongwei Wang2College of Computer Science, Xi’an Shiyou University, Xi’an, ChinaCollege of Computer Science, Xi’an Shiyou University, Xi’an, ChinaCollege of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University, Xi’an, ChinaThe current limited sample set and mixed spatial-spectral information make effective feature extraction in hyperspectral image (HSI) classification challenging. To better extract spatial-spectral features, enhance the robustness of the learned features against the orientation and scale changes and improve the convergence of the network used for HSI classification, we propose a multi-branch hybrid network (MHNet) based on adaptive selection of spatial-spectral kernels in this paper. Specifically, we use the Gabor convolutional layer as the first layer of this network model. Since the predefined multi-scale and multi-directional Gabor filters in this layer can better characterize the internal spatial-spectral structure of HSI data from different perspectives, the robustness of the model to orientation-scale changes is enhanced. Then the performance of joint spatial-spectral feature extraction is improved by learning adaptive selective 3D convolution kernels. Subsequently, a two-branch network is employed to further fully extract spatial and spectral information for classification accuracy. Experimental results on three public hyperspectral datasets show that the proposed MHNet not only has better classification performance than several existing widely used machine learning and deep learning-based methods, but also it has fast model convergence.https://ieeexplore.ieee.org/document/10198228/Multi-branch networkhyperspectral imageselecting spatial-spectral kernelsGaborresidual networkspatial-spectral features |
| spellingShingle | Cailing Wang He Fu Hongwei Wang Multi-Branch Hybrid Network Based on Adaptive Selection of Spatial-Spectral Kernel for Hyperspectral Image Classification IEEE Access Multi-branch network hyperspectral image selecting spatial-spectral kernels Gabor residual network spatial-spectral features |
| title | Multi-Branch Hybrid Network Based on Adaptive Selection of Spatial-Spectral Kernel for Hyperspectral Image Classification |
| title_full | Multi-Branch Hybrid Network Based on Adaptive Selection of Spatial-Spectral Kernel for Hyperspectral Image Classification |
| title_fullStr | Multi-Branch Hybrid Network Based on Adaptive Selection of Spatial-Spectral Kernel for Hyperspectral Image Classification |
| title_full_unstemmed | Multi-Branch Hybrid Network Based on Adaptive Selection of Spatial-Spectral Kernel for Hyperspectral Image Classification |
| title_short | Multi-Branch Hybrid Network Based on Adaptive Selection of Spatial-Spectral Kernel for Hyperspectral Image Classification |
| title_sort | multi branch hybrid network based on adaptive selection of spatial spectral kernel for hyperspectral image classification |
| topic | Multi-branch network hyperspectral image selecting spatial-spectral kernels Gabor residual network spatial-spectral features |
| url | https://ieeexplore.ieee.org/document/10198228/ |
| work_keys_str_mv | AT cailingwang multibranchhybridnetworkbasedonadaptiveselectionofspatialspectralkernelforhyperspectralimageclassification AT hefu multibranchhybridnetworkbasedonadaptiveselectionofspatialspectralkernelforhyperspectralimageclassification AT hongweiwang multibranchhybridnetworkbasedonadaptiveselectionofspatialspectralkernelforhyperspectralimageclassification |