Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/DPT

DPT

Reported on 24 benchmarks across 3 tasks · 1 paper · 2 SOTA

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

Medical20 results

Image GenerationonImageNet 256x256 - 1 labeled data per class
FID-50k
4
Image GenerationonImageNet 256x256 - 1 labeled data per class
IS
178.05
Image GenerationonImageNet 256x256 - 1 labeled data per class
Precision
0.81
Image GenerationonImageNet 256x256 - 1 labeled data per class
Recall
0.53
Image GenerationonImageNet 256x256 - 1 labeled data per class
sFID
6.56
Image GenerationonImageNet 256x256 - 1% labeled data
FID-50k
3.35
Image GenerationonImageNet 256x256 - 1% labeled data
IS
223.09
Image GenerationonImageNet 256x256 - 1% labeled data
Precision
0.83
Image GenerationonImageNet 256x256 - 1% labeled data
Recall
0.52
Image GenerationonImageNet 256x256 - 1% labeled data
sFID
6.66
Image GenerationonImageNet 256x256 - 2 labeled data per class
FID-50k
3.44
Image GenerationonImageNet 256x256 - 2 labeled data per class
IS
199.74
Image GenerationonImageNet 256x256 - 2 labeled data per class
Precision
0.82
Image GenerationonImageNet 256x256 - 2 labeled data per class
Recall
0.53
Image GenerationonImageNet 256x256 - 2 labeled data per class
sFID
6.58
Image GenerationonImageNet 256x256 - 5 labeled data per class
FID-50k
3.37
Image GenerationonImageNet 256x256 - 5 labeled data per class
IS
217.53
Image GenerationonImageNet 256x256 - 5 labeled data per class
Precision
0.83
Image GenerationonImageNet 256x256 - 5 labeled data per class
Recall
0.52
Image GenerationonImageNet 256x256 - 5 labeled data per class
sFID
6.71

Computer Vision2 results

Depth EstimationonETH3D
Delta < 1.25· 2021-03-24
0.0946
best: 0.981 (Distill Any Depth)
SOTA
Vision Transformers for Dense Prediction arXiv:2103.13413
Depth EstimationonETH3D
absolute relative error· 2021-03-24
0.078
best: 0.0121 (HDN)
Vision Transformers for Dense Prediction arXiv:2103.13413

Methodology2 results

3DonETH3D
Delta < 1.25· 2021-03-24
0.0946
best: 0.981 (Distill Any Depth)
SOTA
Vision Transformers for Dense Prediction arXiv:2103.13413
3DonETH3D
absolute relative error· 2021-03-24
0.078
best: 0.0121 (HDN)
Vision Transformers for Dense Prediction arXiv:2103.13413