Adaptive Spectral Correlation Learning Neural Network for Hyperspectral Image Classification
Hyperspectral imagery (HSI), with its rich spectral information across continuous wavelength bands, has become indispensable for fine-grained land cover classification in remote sensing applications. Although some existing deep neural networks have exploited the rich spectral information contained i...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-05-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/17/11/1847 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849722301284614144 |
|---|---|
| author | Wei-Ye Wang Yang-Jun Deng Yuan-Ping Xu Ben-Jun Guo Chao-Long Zhang Heng-Chao Li |
| author_facet | Wei-Ye Wang Yang-Jun Deng Yuan-Ping Xu Ben-Jun Guo Chao-Long Zhang Heng-Chao Li |
| author_sort | Wei-Ye Wang |
| collection | DOAJ |
| description | Hyperspectral imagery (HSI), with its rich spectral information across continuous wavelength bands, has become indispensable for fine-grained land cover classification in remote sensing applications. Although some existing deep neural networks have exploited the rich spectral information contained in HSIs for land cover classification by designing some adaptive learning modules, these modules were usually designed as additional submodules rather than basic structural units for building backbones, and they failed to adaptively model the spectral correlations between adjacent spectral bands and nonadjacent bands from a local and global perspective. To address these issues, a new adaptive spectral-correlation learning neural network (ASLNN) is proposed for HSI classification. Taking advantage of the group convolutional and ConvLSTM3D layers, a new adaptive spectral correlation learning block (ASBlock) is designed as a basic network unit to construct the backbone of a spatial–spectral feature extraction model for learning the spectral information, extracting the spectral-enhanced deep spatial–spectral features. Then, a 3D Gabor filter is utilized to extract heterogeneous spatial–spectral features, and a simple but effective gated asymmetric fusion block (GAFBlock) is further built to align and integrate these two heterogeneous features, thereby achieving competitive classification performance for HSIs. Experimental results from four common hyperspectral data sets validate the effectiveness of the proposed method. Specifically, when 10, 10, 10 and 25 samples from each class are selected for training, ASLNN achieves the highest overall accuracy (OA) of 81.12%, 85.88%, 80.62%, and 97.97% on the four data sets, outperforming other methods with increases of more than 1.70%, 3.21%, 3.78%, and 2.70% in OA, respectively. |
| format | Article |
| id | doaj-art-5355c294ded44a32a2ac8dccb8f8ae46 |
| institution | DOAJ |
| issn | 2072-4292 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-5355c294ded44a32a2ac8dccb8f8ae462025-08-20T03:11:22ZengMDPI AGRemote Sensing2072-42922025-05-011711184710.3390/rs17111847Adaptive Spectral Correlation Learning Neural Network for Hyperspectral Image ClassificationWei-Ye Wang0Yang-Jun Deng1Yuan-Ping Xu2Ben-Jun Guo3Chao-Long Zhang4Heng-Chao Li5School of Software Engineering, Chengdu University of Information Technology, Chengdu 610225, ChinaCollege of Information and Intelligence, Hunan Agricultural University, Changsha 410128, ChinaSchool of Software Engineering, Chengdu University of Information Technology, Chengdu 610225, ChinaSchool of Software Engineering, Chengdu University of Information Technology, Chengdu 610225, ChinaSchool of Software Engineering, Chengdu University of Information Technology, Chengdu 610225, ChinaSchool of Information Science and Technology, Southwest Jiaotong University, Chengdu 611756, ChinaHyperspectral imagery (HSI), with its rich spectral information across continuous wavelength bands, has become indispensable for fine-grained land cover classification in remote sensing applications. Although some existing deep neural networks have exploited the rich spectral information contained in HSIs for land cover classification by designing some adaptive learning modules, these modules were usually designed as additional submodules rather than basic structural units for building backbones, and they failed to adaptively model the spectral correlations between adjacent spectral bands and nonadjacent bands from a local and global perspective. To address these issues, a new adaptive spectral-correlation learning neural network (ASLNN) is proposed for HSI classification. Taking advantage of the group convolutional and ConvLSTM3D layers, a new adaptive spectral correlation learning block (ASBlock) is designed as a basic network unit to construct the backbone of a spatial–spectral feature extraction model for learning the spectral information, extracting the spectral-enhanced deep spatial–spectral features. Then, a 3D Gabor filter is utilized to extract heterogeneous spatial–spectral features, and a simple but effective gated asymmetric fusion block (GAFBlock) is further built to align and integrate these two heterogeneous features, thereby achieving competitive classification performance for HSIs. Experimental results from four common hyperspectral data sets validate the effectiveness of the proposed method. Specifically, when 10, 10, 10 and 25 samples from each class are selected for training, ASLNN achieves the highest overall accuracy (OA) of 81.12%, 85.88%, 80.62%, and 97.97% on the four data sets, outperforming other methods with increases of more than 1.70%, 3.21%, 3.78%, and 2.70% in OA, respectively.https://www.mdpi.com/2072-4292/17/11/1847hyperspectral image classificationdeep neural networksspectral correlation learningheterogeneous feature fusion |
| spellingShingle | Wei-Ye Wang Yang-Jun Deng Yuan-Ping Xu Ben-Jun Guo Chao-Long Zhang Heng-Chao Li Adaptive Spectral Correlation Learning Neural Network for Hyperspectral Image Classification Remote Sensing hyperspectral image classification deep neural networks spectral correlation learning heterogeneous feature fusion |
| title | Adaptive Spectral Correlation Learning Neural Network for Hyperspectral Image Classification |
| title_full | Adaptive Spectral Correlation Learning Neural Network for Hyperspectral Image Classification |
| title_fullStr | Adaptive Spectral Correlation Learning Neural Network for Hyperspectral Image Classification |
| title_full_unstemmed | Adaptive Spectral Correlation Learning Neural Network for Hyperspectral Image Classification |
| title_short | Adaptive Spectral Correlation Learning Neural Network for Hyperspectral Image Classification |
| title_sort | adaptive spectral correlation learning neural network for hyperspectral image classification |
| topic | hyperspectral image classification deep neural networks spectral correlation learning heterogeneous feature fusion |
| url | https://www.mdpi.com/2072-4292/17/11/1847 |
| work_keys_str_mv | AT weiyewang adaptivespectralcorrelationlearningneuralnetworkforhyperspectralimageclassification AT yangjundeng adaptivespectralcorrelationlearningneuralnetworkforhyperspectralimageclassification AT yuanpingxu adaptivespectralcorrelationlearningneuralnetworkforhyperspectralimageclassification AT benjunguo adaptivespectralcorrelationlearningneuralnetworkforhyperspectralimageclassification AT chaolongzhang adaptivespectralcorrelationlearningneuralnetworkforhyperspectralimageclassification AT hengchaoli adaptivespectralcorrelationlearningneuralnetworkforhyperspectralimageclassification |