| Paper | Code | Categorization (ablation) | Categorization (test) | ModelName | ReleaseDate |
|---|---|---|---|---|---|
| Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks | 61.7 | 60.8 | Unified-IOXL | 2022-06-17 | |
| Webly Supervised Concept Expansion for General Purpose Vision Models | 54.7 | 55.1 | GPV-2 | 2022-02-04 | |
| Learning Transferable Visual Models From Natural Language Supervision | ✓ Link | 48.1 | CLIP | 2021-02-26 | |
| OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework | ✓ Link | 22.6 | OFA_Large | 2022-02-07 |