Hyperspectral Image Classification Based on Attentional Residual Networks
Aiming at the problem that the features extracted by the existing convolutional neural Network model are insufficient and the more important information lacks key Attention in the process of hyperspectral image classification, this paper designs an Attention Residual Network (ARN). Firstly, the resi...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10806646/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832590349772521472 |
|---|---|
| author | Ning Wang Xin Pan Xiaoling Luo Xiaojing Gao |
| author_facet | Ning Wang Xin Pan Xiaoling Luo Xiaojing Gao |
| author_sort | Ning Wang |
| collection | DOAJ |
| description | Aiming at the problem that the features extracted by the existing convolutional neural Network model are insufficient and the more important information lacks key Attention in the process of hyperspectral image classification, this paper designs an Attention Residual Network (ARN). Firstly, the residual network is used to extract the features of hyperspectral images, and the quality of feature extraction is effectively improved by solving the problem of gradient disappearance and gradient explosion in deep neural network training. Then, the Attention Module (AM) is introduced to optimize the feature extraction process, so that the model can focus on the important regions in the image. This method was tested on the self-collected Herbage (HB) dataset and the public datasets Indian Pines (IP) and Pavia University (PU), and compared with four classical deep learning classification methods. The experimental results show that the proposed method performs best in hyperspectral image classification and greatly improves the classification accuracy. |
| format | Article |
| id | doaj-art-a43c9c2933814deca6f03cc081091c91 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-a43c9c2933814deca6f03cc081091c912025-01-24T00:01:11ZengIEEEIEEE Access2169-35362025-01-0113106781068810.1109/ACCESS.2024.351978910806646Hyperspectral Image Classification Based on Attentional Residual NetworksNing Wang0Xin Pan1https://orcid.org/0009-0003-4301-6125Xiaoling Luo2https://orcid.org/0009-0007-1903-2407Xiaojing Gao3College of Computer and Information Engineering, Inner Mongolia Agricultural University, Hohhot, ChinaCollege of Computer and Information Engineering, Inner Mongolia Agricultural University, Hohhot, ChinaCollege of Computer and Information Engineering, Inner Mongolia Agricultural University, Hohhot, ChinaCollege of Computer and Information Engineering, Inner Mongolia Agricultural University, Hohhot, ChinaAiming at the problem that the features extracted by the existing convolutional neural Network model are insufficient and the more important information lacks key Attention in the process of hyperspectral image classification, this paper designs an Attention Residual Network (ARN). Firstly, the residual network is used to extract the features of hyperspectral images, and the quality of feature extraction is effectively improved by solving the problem of gradient disappearance and gradient explosion in deep neural network training. Then, the Attention Module (AM) is introduced to optimize the feature extraction process, so that the model can focus on the important regions in the image. This method was tested on the self-collected Herbage (HB) dataset and the public datasets Indian Pines (IP) and Pavia University (PU), and compared with four classical deep learning classification methods. The experimental results show that the proposed method performs best in hyperspectral image classification and greatly improves the classification accuracy.https://ieeexplore.ieee.org/document/10806646/Attention mechanismdeep learninghyperspectral imagesimage classificationresidual networks |
| spellingShingle | Ning Wang Xin Pan Xiaoling Luo Xiaojing Gao Hyperspectral Image Classification Based on Attentional Residual Networks IEEE Access Attention mechanism deep learning hyperspectral images image classification residual networks |
| title | Hyperspectral Image Classification Based on Attentional Residual Networks |
| title_full | Hyperspectral Image Classification Based on Attentional Residual Networks |
| title_fullStr | Hyperspectral Image Classification Based on Attentional Residual Networks |
| title_full_unstemmed | Hyperspectral Image Classification Based on Attentional Residual Networks |
| title_short | Hyperspectral Image Classification Based on Attentional Residual Networks |
| title_sort | hyperspectral image classification based on attentional residual networks |
| topic | Attention mechanism deep learning hyperspectral images image classification residual networks |
| url | https://ieeexplore.ieee.org/document/10806646/ |
| work_keys_str_mv | AT ningwang hyperspectralimageclassificationbasedonattentionalresidualnetworks AT xinpan hyperspectralimageclassificationbasedonattentionalresidualnetworks AT xiaolingluo hyperspectralimageclassificationbasedonattentionalresidualnetworks AT xiaojinggao hyperspectralimageclassificationbasedonattentionalresidualnetworks |