Attention Modules
Cross-Attention Module
Introduced by Chen et al. in CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image ClassificationThe Cross-Attention module is an attention module used in CrossViT for fusion of multi-scale features. The CLS token of the large branch (circle) serves as a query token to interact with the patch tokens from the small branch through attention. $f\left(·\right)$ and $g\left(·\right)$ are projections to align dimensions. The small branch follows the same procedure but swaps CLS and patch tokens from another branch.
Source: CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Decoder | 14 | 6.70% |
| Semantic Segmentation | 10 | 4.78% |
| Retrieval | 7 | 3.35% |
| Object Detection | 7 | 3.35% |
| Image Classification | 6 | 2.87% |
| Autonomous Driving | 5 | 2.39% |
| Image Generation | 4 | 1.91% |
| Image Super-Resolution | 4 | 1.91% |
| Super-Resolution | 4 | 1.91% |
Concatenated Skip Connection
Softmax
