Graph-infused hybrid vision transformer: Advancing GeoAI for enhanced land cover classification
Hyperspectral Image Classification (HSIC) is a challenging task due to the high-dimensional nature of Hyperspectral Imaging (HSI) data and the complex relationships between spectral and spatial information. This paper proposes a Graph-Infused Hybrid spatial–spectral Transformer (GFormer) for HSIC. T...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-05-01
|
| Series: | International Journal of Applied Earth Observations and Geoinformation |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1569843224001274 |
| _version_ | 1797235598157676544 |
|---|---|
| author | Muhammad Hassaan Farooq Butt Jian Ping Li Muhammad Ahmad Muhammad Adnan Farooq Butt |
| author_facet | Muhammad Hassaan Farooq Butt Jian Ping Li Muhammad Ahmad Muhammad Adnan Farooq Butt |
| author_sort | Muhammad Hassaan Farooq Butt |
| collection | DOAJ |
| description | Hyperspectral Image Classification (HSIC) is a challenging task due to the high-dimensional nature of Hyperspectral Imaging (HSI) data and the complex relationships between spectral and spatial information. This paper proposes a Graph-Infused Hybrid spatial–spectral Transformer (GFormer) for HSIC. The GFormer combines the power of graph and spatial–spectral transformer to capture both spectral relationships and spatial context. We represent the HSI data as a graph, where nodes represent pixels and edges capture spectral similarities. By incorporating an attention mechanism, the GFormer learns spatial–spectral fusion representations, allowing it to effectively discriminate between different classes. The model can capture long-range dependencies among spectral bands, enabling it to understand complex interactions in the HSI data. Moreover, the GFormer adapts to different spectral resolutions by dynamically adjusting attention weights for each spectral band. Experimental results on benchmark HSI datasets demonstrate that the GFormer outperforms state-of-the-art (SOTA) methods, achieving superior classification accuracy. |
| first_indexed | 2024-04-24T16:50:30Z |
| format | Article |
| id | doaj.art-492e50e94c684fcca068a6d303df3d56 |
| institution | Directory Open Access Journal |
| issn | 1569-8432 |
| language | English |
| last_indexed | 2024-04-24T16:50:30Z |
| publishDate | 2024-05-01 |
| publisher | Elsevier |
| record_format | Article |
| series | International Journal of Applied Earth Observations and Geoinformation |
| spelling | doaj.art-492e50e94c684fcca068a6d303df3d562024-03-29T05:49:42ZengElsevierInternational Journal of Applied Earth Observations and Geoinformation1569-84322024-05-01129103773Graph-infused hybrid vision transformer: Advancing GeoAI for enhanced land cover classificationMuhammad Hassaan Farooq Butt0Jian Ping Li1Muhammad Ahmad2Muhammad Adnan Farooq Butt3School of Computer Science and Engineering, University of Electronic Science and Technology of China - UESTC, 611731, Sichuan, ChinaSchool of Computer Science and Engineering, University of Electronic Science and Technology of China - UESTC, 611731, Sichuan, China; Corresponding author.Department of Computer Science, National University of Computer and Emerging Sciences, Islamabad, Chiniot-Faisalabad Campus, Chiniot 35400, PakistanInstitute of Artificial Intelligence, School of Mechanical and Electrical Engineering, Shaoxing University, Shaoxing, ChinaHyperspectral Image Classification (HSIC) is a challenging task due to the high-dimensional nature of Hyperspectral Imaging (HSI) data and the complex relationships between spectral and spatial information. This paper proposes a Graph-Infused Hybrid spatial–spectral Transformer (GFormer) for HSIC. The GFormer combines the power of graph and spatial–spectral transformer to capture both spectral relationships and spatial context. We represent the HSI data as a graph, where nodes represent pixels and edges capture spectral similarities. By incorporating an attention mechanism, the GFormer learns spatial–spectral fusion representations, allowing it to effectively discriminate between different classes. The model can capture long-range dependencies among spectral bands, enabling it to understand complex interactions in the HSI data. Moreover, the GFormer adapts to different spectral resolutions by dynamically adjusting attention weights for each spectral band. Experimental results on benchmark HSI datasets demonstrate that the GFormer outperforms state-of-the-art (SOTA) methods, achieving superior classification accuracy.http://www.sciencedirect.com/science/article/pii/S1569843224001274Hyperspectral image classificationSpatial–spectral transformerLand cover classificationVision transformersGraph attention transformers |
| spellingShingle | Muhammad Hassaan Farooq Butt Jian Ping Li Muhammad Ahmad Muhammad Adnan Farooq Butt Graph-infused hybrid vision transformer: Advancing GeoAI for enhanced land cover classification International Journal of Applied Earth Observations and Geoinformation Hyperspectral image classification Spatial–spectral transformer Land cover classification Vision transformers Graph attention transformers |
| title | Graph-infused hybrid vision transformer: Advancing GeoAI for enhanced land cover classification |
| title_full | Graph-infused hybrid vision transformer: Advancing GeoAI for enhanced land cover classification |
| title_fullStr | Graph-infused hybrid vision transformer: Advancing GeoAI for enhanced land cover classification |
| title_full_unstemmed | Graph-infused hybrid vision transformer: Advancing GeoAI for enhanced land cover classification |
| title_short | Graph-infused hybrid vision transformer: Advancing GeoAI for enhanced land cover classification |
| title_sort | graph infused hybrid vision transformer advancing geoai for enhanced land cover classification |
| topic | Hyperspectral image classification Spatial–spectral transformer Land cover classification Vision transformers Graph attention transformers |
| url | http://www.sciencedirect.com/science/article/pii/S1569843224001274 |
| work_keys_str_mv | AT muhammadhassaanfarooqbutt graphinfusedhybridvisiontransformeradvancinggeoaiforenhancedlandcoverclassification AT jianpingli graphinfusedhybridvisiontransformeradvancinggeoaiforenhancedlandcoverclassification AT muhammadahmad graphinfusedhybridvisiontransformeradvancinggeoaiforenhancedlandcoverclassification AT muhammadadnanfarooqbutt graphinfusedhybridvisiontransformeradvancinggeoaiforenhancedlandcoverclassification |