Visual Prompt Tuning On Vtab 1K Specialized 4
Metrics
Mean Accuracy
Results
Performance results of various models on this benchmark
| Paper Title | ||
|---|---|---|
| SPT-Deep(ViT-B/16_MoCo_v3_pretrained_ImageNet-1K) | 84.95 | Revisiting the Power of Prompt for Visual Tuning |
| SPT-Shallow(ViT-B/16_MoCo_v3_pretrained_ImageNet-1K) | 83.93 | Revisiting the Power of Prompt for Visual Tuning |
| GateVPT(ViT-B/16_MoCo_v3_pretrained_ImageNet-1K) | 83.38 | Improving Visual Prompt Tuning for Self-supervised Vision Transformers |
| SPT-Deep(ViT-B/16_MAE_pretrained_ImageNet-1K) | 83.15 | Revisiting the Power of Prompt for Visual Tuning |
| VPT-Deep(ViT-B/16_MoCo_v3_pretrained_ImageNet-1K) | 83.04 | Visual Prompt Tuning |
| VPT-Shallow(ViT-B/16_MoCo_v3_pretrained_ImageNet-1K) | 82.26 | Visual Prompt Tuning |
| SPT-Shallow(ViT-B/16_MAE_pretrained_ImageNet-1K) | 80.90 | Revisiting the Power of Prompt for Visual Tuning |
| GateVPT(ViT-B/16_MAE_pretrained_ImageNet-1K) | 76.86 | Improving Visual Prompt Tuning for Self-supervised Vision Transformers |
| VPT-Shallow(ViT-B/16_MAE_pretrained_ImageNet-1K) | 69.65 | Visual Prompt Tuning |
| VPT-Deep(ViT-B/16_MAE_pretrained_ImageNet-1K) | 60.61 | Visual Prompt Tuning |
0 of 10 row(s) selected.