PGT (Swin-T)

Reported on 5 benchmarks across 5 tasks · 1 paper

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

Computer Vision2 results

Depth EstimationonNYU-Depth V2
RMSE· 2023-07-28
0.59
best: 0.013 (Defocus/DepthNet (Normalized))
Prompt Guided Transformer for Multi-Task Dense Prediction arXiv:2307.15362
Boundary DetectiononNYU-Depth V2
odsF· 2023-07-28
77.05
best: 78.1 (InvPT)
Prompt Guided Transformer for Multi-Task Dense Prediction arXiv:2307.15362

Medical1 result

Semantic SegmentationonNYU Depth v2
Mean IoU· 2023-07-28
41.61
best: 63.6 (OmniVec2)
Prompt Guided Transformer for Multi-Task Dense Prediction arXiv:2307.15362

Methodology1 result

3DonNYU-Depth V2
RMSE· 2023-07-28
0.59
best: 0.013 (Defocus/DepthNet (Normalized))
Prompt Guided Transformer for Multi-Task Dense Prediction arXiv:2307.15362

Audio1 result

10-shot image generationonNYU Depth v2
Mean IoU· 2023-07-28
41.61
best: 63.6 (OmniVec2)
Prompt Guided Transformer for Multi-Task Dense Prediction arXiv:2307.15362