GateVPT(ViT-B/16_MAE_pretrained_ImageNet-1K)

Reported on 4 benchmarks across 1 task · 1 paper

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· 2023-06-08
73.39
best: 86 (SPT-Deep(ViT-B/16_MoCo_v3_pretrained_ImageNet-1K))
Improving Visual Prompt Tuning for Self-supervised Vision Transformers arXiv:2306.05067
Visual Prompt TuningonVTAB-1k(Structured<8>)
Mean Accuracy· 2023-06-08
36.8
best: 59.23 (SPT-Deep(ViT-B/16_MAE_pretrained_ImageNet-1K))
Improving Visual Prompt Tuning for Self-supervised Vision Transformers arXiv:2306.05067
Visual Prompt TuningonVTAB-1k(Natural<7>)
Mean Accuracy· 2023-06-08
47.61
best: 76.2 (SPT-Deep(ViT-B/16_MoCo_v3_pretrained_ImageNet-1K))
Improving Visual Prompt Tuning for Self-supervised Vision Transformers arXiv:2306.05067
Visual Prompt TuningonVTAB-1k(Specialized<4>)
Mean Accuracy· 2023-06-08
76.86
best: 84.95 (SPT-Deep(ViT-B/16_MoCo_v3_pretrained_ImageNet-1K))
Improving Visual Prompt Tuning for Self-supervised Vision Transformers arXiv:2306.05067