Multi-head Spatial-Spectral Mamba for Hyperspectral Image Classification
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909479448084480 |
|---|---|
| author | Ahmad, Muhammad Butt, Muhammad Hassaan Farooq Usama, Muhammad Altuwaijri, Hamad Ahmed Mazzara, Manuel Distefano, Salvatore |
| author_facet | Ahmad, Muhammad Butt, Muhammad Hassaan Farooq Usama, Muhammad Altuwaijri, Hamad Ahmed Mazzara, Manuel Distefano, Salvatore |
| contents | Spatial-Spectral Mamba (SSM) improves computational efficiency and captures long-range dependencies, addressing Transformer limitations. However, traditional Mamba models overlook rich spectral information in HSIs and struggle with high dimensionality and sequential data. To address these issues, we propose the SSM with multi-head self-attention and token enhancement (MHSSMamba). This model integrates spectral and spatial information by enhancing spectral tokens and using multi-head attention to capture complex relationships between spectral bands and spatial locations. It also manages long-range dependencies and the sequential nature of HSI data, preserving contextual information across spectral bands. MHSSMamba achieved remarkable classification accuracies of 97.62\% on Pavia University, 96.92\% on the University of Houston, 96.85\% on Salinas, and 99.49\% on Wuhan-longKou datasets. The source code is available at \href{https://github.com/MHassaanButt/MHA\_SS\_Mamba}{GitHub}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_01224 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Multi-head Spatial-Spectral Mamba for Hyperspectral Image Classification Ahmad, Muhammad Butt, Muhammad Hassaan Farooq Usama, Muhammad Altuwaijri, Hamad Ahmed Mazzara, Manuel Distefano, Salvatore Computer Vision and Pattern Recognition Spatial-Spectral Mamba (SSM) improves computational efficiency and captures long-range dependencies, addressing Transformer limitations. However, traditional Mamba models overlook rich spectral information in HSIs and struggle with high dimensionality and sequential data. To address these issues, we propose the SSM with multi-head self-attention and token enhancement (MHSSMamba). This model integrates spectral and spatial information by enhancing spectral tokens and using multi-head attention to capture complex relationships between spectral bands and spatial locations. It also manages long-range dependencies and the sequential nature of HSI data, preserving contextual information across spectral bands. MHSSMamba achieved remarkable classification accuracies of 97.62\% on Pavia University, 96.92\% on the University of Houston, 96.85\% on Salinas, and 99.49\% on Wuhan-longKou datasets. The source code is available at \href{https://github.com/MHassaanButt/MHA\_SS\_Mamba}{GitHub}. |
| title | Multi-head Spatial-Spectral Mamba for Hyperspectral Image Classification |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.01224 |