CGA-ViT: Channel-Guided Additive Attention for Efficient Vision Recognition
Vision transformers (ViTs) excel at global context modeling with self-attention. However, standard self-attention leads to quadratic computational complexity, which restricts its practical use in high-resolution or latency-sensitive tasks. Existing methods achieve linear complexity via local window...
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Artigo |
| Lenguaje: | Inglês |
| Publicado: |
MDPI AG
2026-02-01
|
| Colección: | Applied Sciences |
| Materias: | |
| Acceso en línea: | https://www.mdpi.com/2076-3417/16/4/1740 |
| Etiquetas: |
Sin Etiquetas, Sea el primero en etiquetar este registro!
|