| Paper | Code | Localization (ablation) | Localization (test) | ModelName | ReleaseDate |
|---|---|---|---|---|---|
| Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks | 67.0 | 67.1 | Unified-IOXL | 2022-06-17 | |
| Webly Supervised Concept Expansion for General Purpose Vision Models | 53.6 | 53.6 | GPV-2 | 2022-02-04 | |
| Mask R-CNN | ✓ Link | 44.7 | 45.1 | Mask R-CNN | 2017-03-20 |