| Paper | Code | Accuracy | ModelName | ReleaseDate |
|---|---|---|---|---|
| FLAVA: A Foundational Language And Vision Alignment Model | ✓ Link | 82.17 | FLAVA | 2021-12-08 |
| Multi-label Cluster Discrimination for Visual Representation Learning | ✓ Link | 82.1 | MLCD ViT-L/14 (linear probe) | 2024-07-24 |
| DINOv3 | ✓ Link | 81.1 | DINOv3 (7B) | 2025-08-13 |
| PolyViT: Co-training Vision Transformers on Images, Videos and Audio | 80.0 | PolyViT-Base (image tasks) linear probe | 2021-11-25 | |
| Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision | ✓ Link | 80.0 | SEER (RegNet10B - linear eval) | 2022-02-16 |
| DINOv2: Learning Robust Visual Features without Supervision | ✓ Link | 78.7 | DINOv2 (ViT-g/14) | 2023-04-14 |