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

Reported on 4 benchmarks across 1 task · 1 paper · 3 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· 2024-02-04
86
SOTA
Revisiting the Power of Prompt for Visual Tuning arXiv:2402.02382
Visual Prompt TuningonVTAB-1k(Natural<7>)
Mean Accuracy· 2024-02-04
76.2
SOTA
Revisiting the Power of Prompt for Visual Tuning arXiv:2402.02382
Visual Prompt TuningonVTAB-1k(Specialized<4>)
Mean Accuracy· 2024-02-04
84.95
SOTA
Revisiting the Power of Prompt for Visual Tuning arXiv:2402.02382
Visual Prompt TuningonVTAB-1k(Structured<8>)
Mean Accuracy· 2024-02-04
58.36
best: 59.23 (SPT-Deep(ViT-B/16_MAE_pretrained_ImageNet-1K))
Revisiting the Power of Prompt for Visual Tuning arXiv:2402.02382