Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2504.18770 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912347220606976 |
|---|---|
| author | Weber, Manuel Beneke, Carly |
| author_facet | Weber, Manuel Beneke, Carly |
| contents | We propose PyViT-FUSE, a foundation model for earth observation data explicitly designed to handle multi-modal imagery by learning to fuse an arbitrary number of mixed-resolution input bands into a single representation through an attention mechanism. The learned patch tokens are further processed by a stack of vision transformers with a novel pyramidal structure. We train the model on a globally sampled dataset in a self-supervised manner, leveraging core concepts of the SwAV algorithm. We show the interpretability of the fusion mechanism by visualization of the attention scores and the models applicability to downstream tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_18770 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PyViT-FUSE: A Foundation Model for Multi-Sensor Earth Observation Data Weber, Manuel Beneke, Carly Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning We propose PyViT-FUSE, a foundation model for earth observation data explicitly designed to handle multi-modal imagery by learning to fuse an arbitrary number of mixed-resolution input bands into a single representation through an attention mechanism. The learned patch tokens are further processed by a stack of vision transformers with a novel pyramidal structure. We train the model on a globally sampled dataset in a self-supervised manner, leveraging core concepts of the SwAV algorithm. We show the interpretability of the fusion mechanism by visualization of the attention scores and the models applicability to downstream tasks. |
| title | PyViT-FUSE: A Foundation Model for Multi-Sensor Earth Observation Data |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2504.18770 |