| Benchmark | Model | Rank | Results |
|---|---|---|---|
| object-counting-on-clevr-count | SPT-LoRA ViT-B/16 (VTAB-1k) | #1 | Accuracy: 84.4 |
| monocular-depth-estimation-on-clevr-distance | SPT-Adapter ViT-B/16 (VTAB-1k) | #2 | Accuracy: 68.0 |
| image-classification-on-vtab-1k-group-mean | SPT-Adapter | #3 | Accuracy: 76.4 |