| Paper | Code | Accuracy | ModelName | ReleaseDate |
|---|---|---|---|---|
| DINOv2: Learning Robust Visual Features without Supervision | ✓ Link | 97.6 | DINOv2 (ViT-g/14) | 2023-04-14 |
| Multi-label Cluster Discrimination for Visual Representation Learning | ✓ Link | 97.2 | MLCD ViT-L/14 (linear probe) | 2024-07-24 |
| FLAVA: A Foundational Language And Vision Alignment Model | ✓ Link | 95.74 | FLAVA | 2021-12-08 |
| DINOv3 | ✓ Link | 94.8 | DINOv3 (7B) | 2025-08-13 |
| PolyViT: Co-training Vision Transformers on Images, Videos and Audio | 91.0 | PolyViT-Base (L_adapt=0) linear probe | 2021-11-25 |