Image Models
PoolFormer
Introduced by Yu et al. in MetaFormer Is Actually What You Need for VisionPoolFormer is instantiated from MetaFormer by specifying the token mixer as extremely simple operator, pooling. PoolFormer is utilized as a tool to verify MetaFormer hypothesis "MetaFormer is actually what you need" (vs "Attention is all you need").
Source: MetaFormer Is Actually What You Need for Vision
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Image Classification | 3 | 37.50% |
| Semantic Segmentation | 2 | 25.00% |
| Scene Classification | 1 | 12.50% |
| Spatial Token Mixer | 1 | 12.50% |
| Object Detection | 1 | 12.50% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
