| Paper | Code | Accuracy | ModelName | ReleaseDate |
|---|---|---|---|---|
| Multi-label Cluster Discrimination for Visual Representation Learning | ✓ Link | 84.6 | MLCD ViT-L/14 (linear probe) | 2024-07-24 |
| DINOv2: Learning Robust Visual Features without Supervision | ✓ Link | 84.5 | DINOv2 (ViT-g/14) | 2023-04-14 |
| FLAVA: A Foundational Language And Vision Alignment Model | ✓ Link | 77.29 | FLAVA | 2021-12-08 |
| $λ$-JEPA Spectral Anti-Collapse Regularization for Self-Supervised Learning | ✓ Link | 73.2 | λ-JEPA ViT-B/16 (linear probe) | 2026-09-28 |
| PolyViT: Co-training Vision Transformers on Images, Videos and Audio | 72.5 | PolyViT-Base (image tasks) linear probe | 2021-11-25 |