Faster than Light: An Embedded-Efficient Matching Model with ReLU Linear Attention
Deep learning-based image matching faces a critical challenge when deployed on computationally constrained embedded aerial devices. Transformer-based architectures, particularly the scaled dot-product attention mechanism, incur high computational costs that limit inference speed for real-time applic...
Збережено в:
| Автори: | , , , , , |
|---|---|
| Формат: | Artigo |
| Мова: | Inglês |
| Опубліковано: |
Copernicus Publications
2026-07-01
|
| Серія: | ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| Онлайн доступ: | https://isprs-annals.copernicus.org/articles/XI-2-2026/45/2026/isprs-annals-XI-2-2026-45-2026.pdf |
| Теги: |
Немає тегів, Будьте першим, хто поставить тег для цього запису!
|