Few Shot Image Classification On Imagenet 5
Metriken
Top 1 Accuracy
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Modellname | Top 1 Accuracy | Paper Title | Repository |
|---|---|---|---|
| V-MoE-H/14 (Every-2) | 78.21 | Scaling Vision with Sparse Mixture of Experts | |
| ViT-MoE-15B (Every-2) | 82.78 | Scaling Vision with Sparse Mixture of Experts | |
| V-MoE-L/16 (Every-2) | 77.1 | Scaling Vision with Sparse Mixture of Experts | |
| MAWS (ViT-H) | 79.8 | The effectiveness of MAE pre-pretraining for billion-scale pretraining | |
| V-MoE-H/14 (Last-5) | 78.08 | Scaling Vision with Sparse Mixture of Experts | |
| VIT-H/14 | 76.95 | Scaling Vision with Sparse Mixture of Experts | |
| MAWS (ViT-2B) | 81.5 | The effectiveness of MAE pre-pretraining for billion-scale pretraining | |
| MAWS (ViT-6.5B) | 82.6 | The effectiveness of MAE pre-pretraining for billion-scale pretraining |
0 of 8 row(s) selected.