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...
| Published in: | IEEE Access |
|---|---|
| Main Authors: | , |
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10254205/ |