Discrete Wavelet Transform Meets Transformer: Unleashing the Full Potential of the Transformer for Visual Recognition
Traditionally, the success of the Transformer has been attributed to its token mixer, particularly the self-attention mechanism. However, recent studies suggest that replacing such attention-based token mixer with alternative techniques can yield comparable results in various vision tasks. This high...
Na minha lista:
| Principais autores: | , |
|---|---|
| Formato: | Artigo |
| Idioma: | Inglês |
| Publicado em: |
IEEE
2023-01-01
|
| Colecção: | IEEE Access |
| Assuntos: | |
| Acesso em linha: | https://ieeexplore.ieee.org/document/10254205/ |
| Tags: |
Sem tags, seja o primeiro a adicionar uma tag!
|