Image Models
MetaFormer
Introduced by Yu et al. in MetaFormer Is Actually What You Need for VisionMetaFormer is a general architecture abstracted from Transformers by not specifying the token mixer.
Source: MetaFormer Is Actually What You Need for Vision
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Image Classification | 6 | 30.00% |
| Semantic Segmentation | 3 | 15.00% |
| Object Detection | 2 | 10.00% |
| Object Recognition | 1 | 5.00% |
| Image Categorization | 1 | 5.00% |
| Decision Making | 1 | 5.00% |
| Reinforcement Learning (RL) | 1 | 5.00% |
| Image Segmentation | 1 | 5.00% |
| Medical Image Segmentation | 1 | 5.00% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
