3-D Channel and Spatial Attention Based Multiscale Spatial–Spectral Residual Network for Hyperspectral Image Classification
With the rapid development of aerospace and various remote sensing platforms, the amount of data related to remote sensing is increasing rapidly. To meet the application requirements of remote sensing big data, an increasing number of scholars are combining deep learning with remote sensing data. In...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9149648/ |
| _version_ | 1819137287171080192 |
|---|---|
| author | Zhenyu Lu Bin Xu Le Sun Tianming Zhan Songze Tang |
| author_facet | Zhenyu Lu Bin Xu Le Sun Tianming Zhan Songze Tang |
| author_sort | Zhenyu Lu |
| collection | DOAJ |
| description | With the rapid development of aerospace and various remote sensing platforms, the amount of data related to remote sensing is increasing rapidly. To meet the application requirements of remote sensing big data, an increasing number of scholars are combining deep learning with remote sensing data. In recent years, based on the rapid development of deep learning methods, research in the field of hyperspectral image (HSI) classification has seen continuous breakthroughs. In order to fully extract the characteristics of HSIs and improve the accuracy of image classification, this article proposes a novel three-dimensional (3-D) channel and spatial attention-based multiscale spatial-spectral residual network (termed CSMS-SSRN). The CSMS-SSRN framework uses a three-layer parallel residual network structure by using different 3-D convolutional kernels to continuously learn spectral and spatial features from their respective residual blocks. Then, the extracted depth multiscale features are stacked and input into the 3-D attention module to enhance the expressiveness of the image features from the two aspects of channel and spatial domains, thereby improving the accuracy of classification. The CSMS-SSRN framework proposed in this article can achieve better classification performance on different HSI datasets. |
| first_indexed | 2024-12-22T10:48:28Z |
| format | Article |
| id | doaj.art-ae52a3b3758440c7bd63c65ea041eb44 |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-12-22T10:48:28Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-ae52a3b3758440c7bd63c65ea041eb442022-12-21T18:28:52ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352020-01-01134311432410.1109/JSTARS.2020.301199291496483-D Channel and Spatial Attention Based Multiscale Spatial–Spectral Residual Network for Hyperspectral Image ClassificationZhenyu Lu0Bin Xu1Le Sun2https://orcid.org/0000-0001-6465-8678Tianming Zhan3https://orcid.org/0000-0001-5030-3032Songze Tang4School of Artificial Intelligence, Nanjing University of Information Science and Technology, Nanjing, ChinaSchool of Electronic and Information Engineering, Nanjing University of Information Science and Technology, Nanjing, ChinaSchool of Computer and Software, Nanjing University of Information Science and Technology, Nanjing, ChinaSchool of Information Engineering, Nanjing Audit University, Nanjing, ChinaCollege of Nanjing Forest Police, Nanjing Forest Police College, Nanjing, ChinaWith the rapid development of aerospace and various remote sensing platforms, the amount of data related to remote sensing is increasing rapidly. To meet the application requirements of remote sensing big data, an increasing number of scholars are combining deep learning with remote sensing data. In recent years, based on the rapid development of deep learning methods, research in the field of hyperspectral image (HSI) classification has seen continuous breakthroughs. In order to fully extract the characteristics of HSIs and improve the accuracy of image classification, this article proposes a novel three-dimensional (3-D) channel and spatial attention-based multiscale spatial-spectral residual network (termed CSMS-SSRN). The CSMS-SSRN framework uses a three-layer parallel residual network structure by using different 3-D convolutional kernels to continuously learn spectral and spatial features from their respective residual blocks. Then, the extracted depth multiscale features are stacked and input into the 3-D attention module to enhance the expressiveness of the image features from the two aspects of channel and spatial domains, thereby improving the accuracy of classification. The CSMS-SSRN framework proposed in this article can achieve better classification performance on different HSI datasets.https://ieeexplore.ieee.org/document/9149648/Attentiondeep learninghyperspectral imagemultiscale spatial–spectral residual network |
| spellingShingle | Zhenyu Lu Bin Xu Le Sun Tianming Zhan Songze Tang 3-D Channel and Spatial Attention Based Multiscale Spatial–Spectral Residual Network for Hyperspectral Image Classification IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Attention deep learning hyperspectral image multiscale spatial–spectral residual network |
| title | 3-D Channel and Spatial Attention Based Multiscale Spatial–Spectral Residual Network for Hyperspectral Image Classification |
| title_full | 3-D Channel and Spatial Attention Based Multiscale Spatial–Spectral Residual Network for Hyperspectral Image Classification |
| title_fullStr | 3-D Channel and Spatial Attention Based Multiscale Spatial–Spectral Residual Network for Hyperspectral Image Classification |
| title_full_unstemmed | 3-D Channel and Spatial Attention Based Multiscale Spatial–Spectral Residual Network for Hyperspectral Image Classification |
| title_short | 3-D Channel and Spatial Attention Based Multiscale Spatial–Spectral Residual Network for Hyperspectral Image Classification |
| title_sort | 3 d channel and spatial attention based multiscale spatial x2013 spectral residual network for hyperspectral image classification |
| topic | Attention deep learning hyperspectral image multiscale spatial–spectral residual network |
| url | https://ieeexplore.ieee.org/document/9149648/ |
| work_keys_str_mv | AT zhenyulu 3dchannelandspatialattentionbasedmultiscalespatialx2013spectralresidualnetworkforhyperspectralimageclassification AT binxu 3dchannelandspatialattentionbasedmultiscalespatialx2013spectralresidualnetworkforhyperspectralimageclassification AT lesun 3dchannelandspatialattentionbasedmultiscalespatialx2013spectralresidualnetworkforhyperspectralimageclassification AT tianmingzhan 3dchannelandspatialattentionbasedmultiscalespatialx2013spectralresidualnetworkforhyperspectralimageclassification AT songzetang 3dchannelandspatialattentionbasedmultiscalespatialx2013spectralresidualnetworkforhyperspectralimageclassification |