vision suite
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Multi-task Image Classification | 8-task vision suite | Average Performance94.3 | 28 | |
| Image Classification | 8-task vision suite CLIP ViT-L/14 (test) | SUN397 Accuracy82.3 | 14 | |
| Vision Classification | 30-task Vision Suite (10 unseen tasks) | Accuracy55.4 | 8 | |
| Vision Classification | 30-task vision suite (20 seen tasks) | Accuracy89 | 8 | |
| Image Classification | 8-task vision suite | Accuracy85.9 | 4 |
Showing 5 of 5 rows