Metric: Top 1 Accuracy (higher is better)
| # | Model↕ | Top 1 Accuracy▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | SWAG (ViT H/14) | 60.7 | Yes | Revisiting Weakly Supervised Pre-Training of Vis... | 2022-01-20 | Code |
| 2 | Hiera-H (448px) | 60.6 | Yes | Hiera: A Hierarchical Vision Transformer without... | 2023-06-01 | Code |
| 3 | MAE (ViT-H, 448) | 60.3 | Yes | Masked Autoencoders Are Scalable Vision Learners | 2021-11-11 | Code |
| 4 | WaveMix-240/12 (level 4) | 56.45 | No | WaveMix: A Resource-efficient Neural Network for... | 2022-05-28 | Code |