Transformer-Guided Content-Adaptive Graph Learning for Hyperspectral Unmixing
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912569103482880 |
|---|---|
| author | Chen, Hui Liu, Liangyu Xiu, Xianchao Liu, Wanquan |
| author_facet | Chen, Hui Liu, Liangyu Xiu, Xianchao Liu, Wanquan |
| contents | Hyperspectral unmixing (HU) targets to decompose each mixed pixel in remote sensing images into a set of endmembers and their corresponding abundances. Despite significant progress in this field using deep learning, most methods fail to simultaneously characterize global dependencies and local consistency, making it difficult to preserve both long-range interactions and boundary details. This letter proposes a novel transformer-guided content-adaptive graph unmixing framework (T-CAGU), which overcomes these challenges by employing a transformer to capture global dependencies and introducing a content-adaptive graph neural network to enhance local relationships. Unlike previous work, T-CAGU integrates multiple propagation orders to dynamically learn the graph structure, ensuring robustness against noise. Furthermore, T-CAGU leverages a graph residual mechanism to preserve global information and stabilize training. Experimental results demonstrate its superiority over the state-of-the-art methods. Our code is available at https://github.com/xianchaoxiu/T-CAGU. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_03376 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Transformer-Guided Content-Adaptive Graph Learning for Hyperspectral Unmixing Chen, Hui Liu, Liangyu Xiu, Xianchao Liu, Wanquan Computer Vision and Pattern Recognition Hyperspectral unmixing (HU) targets to decompose each mixed pixel in remote sensing images into a set of endmembers and their corresponding abundances. Despite significant progress in this field using deep learning, most methods fail to simultaneously characterize global dependencies and local consistency, making it difficult to preserve both long-range interactions and boundary details. This letter proposes a novel transformer-guided content-adaptive graph unmixing framework (T-CAGU), which overcomes these challenges by employing a transformer to capture global dependencies and introducing a content-adaptive graph neural network to enhance local relationships. Unlike previous work, T-CAGU integrates multiple propagation orders to dynamically learn the graph structure, ensuring robustness against noise. Furthermore, T-CAGU leverages a graph residual mechanism to preserve global information and stabilize training. Experimental results demonstrate its superiority over the state-of-the-art methods. Our code is available at https://github.com/xianchaoxiu/T-CAGU. |
| title | Transformer-Guided Content-Adaptive Graph Learning for Hyperspectral Unmixing |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.03376 |