<i>H<sup>2</sup>A<sup>2</sup></i>Net: A Hybrid Convolution and Hybrid Resolution Network with Double Attention for Hyperspectral Image Classification
Deep learning (DL) has recently been a core ingredient in modern computer vision tasks, triggering a wave of revolutions in various fields. The hyperspectral image (HSI) classification task is no exception. A wide range of DL-based methods have shone brilliantly in HSI classification. However, under...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-08-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/17/4235 |
| _version_ | 1797493340522938368 |
|---|---|
| author | Hao Shi Guo Cao Youqiang Zhang Zixian Ge Yanbo Liu Peng Fu |
| author_facet | Hao Shi Guo Cao Youqiang Zhang Zixian Ge Yanbo Liu Peng Fu |
| author_sort | Hao Shi |
| collection | DOAJ |
| description | Deep learning (DL) has recently been a core ingredient in modern computer vision tasks, triggering a wave of revolutions in various fields. The hyperspectral image (HSI) classification task is no exception. A wide range of DL-based methods have shone brilliantly in HSI classification. However, understanding how to better exploit spectral and spatial information regarding HSI is still an open area of enquiry. In this article, we propose a hybrid convolution and hybrid resolution network with double attention for HSI classification. First, densely connected 3D convolutional layers are employed to extract preliminary spatial–spectral features. Second, these coarse features are fed to the hybrid resolution module, which mines the features at multiple scales to obtain high-level semantic information and low-level local information. Finally, we introduce a novel attention mechanism for further feature adjustment and refinement. Extensive experiments are conducted to evaluate our model in a holistic manner. Compared to several popular methods, our approach yields promising results for four datasets. |
| first_indexed | 2024-03-10T01:18:37Z |
| format | Article |
| id | doaj.art-002c7392a7e848fa9ffd9bc2a7dec0a1 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T01:18:37Z |
| publishDate | 2022-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-002c7392a7e848fa9ffd9bc2a7dec0a12023-11-23T14:03:13ZengMDPI AGRemote Sensing2072-42922022-08-011417423510.3390/rs14174235<i>H<sup>2</sup>A<sup>2</sup></i>Net: A Hybrid Convolution and Hybrid Resolution Network with Double Attention for Hyperspectral Image ClassificationHao Shi0Guo Cao1Youqiang Zhang2Zixian Ge3Yanbo Liu4Peng Fu5School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, ChinaSchool of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, ChinaSchool of the Internet of Things, Nanjing University of Posts and Telecommunications, Nanjing 210003, ChinaSchool of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, ChinaSchool of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, ChinaSchool of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, ChinaDeep learning (DL) has recently been a core ingredient in modern computer vision tasks, triggering a wave of revolutions in various fields. The hyperspectral image (HSI) classification task is no exception. A wide range of DL-based methods have shone brilliantly in HSI classification. However, understanding how to better exploit spectral and spatial information regarding HSI is still an open area of enquiry. In this article, we propose a hybrid convolution and hybrid resolution network with double attention for HSI classification. First, densely connected 3D convolutional layers are employed to extract preliminary spatial–spectral features. Second, these coarse features are fed to the hybrid resolution module, which mines the features at multiple scales to obtain high-level semantic information and low-level local information. Finally, we introduce a novel attention mechanism for further feature adjustment and refinement. Extensive experiments are conducted to evaluate our model in a holistic manner. Compared to several popular methods, our approach yields promising results for four datasets.https://www.mdpi.com/2072-4292/14/17/4235hyperspectral image (HSI) classificationdeep learningconvolutional neural networkhybrid resolutionattention mechanismfeature fusion |
| spellingShingle | Hao Shi Guo Cao Youqiang Zhang Zixian Ge Yanbo Liu Peng Fu <i>H<sup>2</sup>A<sup>2</sup></i>Net: A Hybrid Convolution and Hybrid Resolution Network with Double Attention for Hyperspectral Image Classification Remote Sensing hyperspectral image (HSI) classification deep learning convolutional neural network hybrid resolution attention mechanism feature fusion |
| title | <i>H<sup>2</sup>A<sup>2</sup></i>Net: A Hybrid Convolution and Hybrid Resolution Network with Double Attention for Hyperspectral Image Classification |
| title_full | <i>H<sup>2</sup>A<sup>2</sup></i>Net: A Hybrid Convolution and Hybrid Resolution Network with Double Attention for Hyperspectral Image Classification |
| title_fullStr | <i>H<sup>2</sup>A<sup>2</sup></i>Net: A Hybrid Convolution and Hybrid Resolution Network with Double Attention for Hyperspectral Image Classification |
| title_full_unstemmed | <i>H<sup>2</sup>A<sup>2</sup></i>Net: A Hybrid Convolution and Hybrid Resolution Network with Double Attention for Hyperspectral Image Classification |
| title_short | <i>H<sup>2</sup>A<sup>2</sup></i>Net: A Hybrid Convolution and Hybrid Resolution Network with Double Attention for Hyperspectral Image Classification |
| title_sort | i h sup 2 sup a sup 2 sup i net a hybrid convolution and hybrid resolution network with double attention for hyperspectral image classification |
| topic | hyperspectral image (HSI) classification deep learning convolutional neural network hybrid resolution attention mechanism feature fusion |
| url | https://www.mdpi.com/2072-4292/14/17/4235 |
| work_keys_str_mv | AT haoshi ihsup2supasup2supinetahybridconvolutionandhybridresolutionnetworkwithdoubleattentionforhyperspectralimageclassification AT guocao ihsup2supasup2supinetahybridconvolutionandhybridresolutionnetworkwithdoubleattentionforhyperspectralimageclassification AT youqiangzhang ihsup2supasup2supinetahybridconvolutionandhybridresolutionnetworkwithdoubleattentionforhyperspectralimageclassification AT zixiange ihsup2supasup2supinetahybridconvolutionandhybridresolutionnetworkwithdoubleattentionforhyperspectralimageclassification AT yanboliu ihsup2supasup2supinetahybridconvolutionandhybridresolutionnetworkwithdoubleattentionforhyperspectralimageclassification AT pengfu ihsup2supasup2supinetahybridconvolutionandhybridresolutionnetworkwithdoubleattentionforhyperspectralimageclassification |