VPT-Deep(ViT-B/16_MoCo_v3_pretrained_ImageNet-1K)

Reported on 4 benchmarks across 1 task · 1 paper · 4 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision4 results

Visual Prompt TuningonFGVC
Mean Accuracy· 2022-03-23
83.12
best: 86 (SPT-Deep(ViT-B/16_MoCo_v3_pretrained_ImageNet-1K))
SOTA
Visual Prompt Tuning arXiv:2203.12119
Visual Prompt TuningonVTAB-1k(Structured<8>)
Mean Accuracy· 2022-03-23
42.38
best: 59.23 (SPT-Deep(ViT-B/16_MAE_pretrained_ImageNet-1K))
SOTA
Visual Prompt Tuning arXiv:2203.12119
Visual Prompt TuningonVTAB-1k(Natural<7>)
Mean Accuracy· 2022-03-23
70.27
best: 76.2 (SPT-Deep(ViT-B/16_MoCo_v3_pretrained_ImageNet-1K))
SOTA
Visual Prompt Tuning arXiv:2203.12119
Visual Prompt TuningonVTAB-1k(Specialized<4>)
Mean Accuracy· 2022-03-23
83.04
best: 84.95 (SPT-Deep(ViT-B/16_MoCo_v3_pretrained_ImageNet-1K))
SOTA
Visual Prompt Tuning arXiv:2203.12119