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-Hybrid

DPT-Hybrid

Reported on 32 benchmarks across 4 tasks · 1 paper · 6 SOTA

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

Computer Vision12 results

Depth EstimationonNYU-Depth V2
Delta < 1.25^2· uses extra data· 2021-03-24
0.988
best: 1 (HybridDepth)
SOTA
Vision Transformers for Dense Prediction arXiv:2103.13413
Depth EstimationonNYU-Depth V2
Delta < 1.25· uses extra data· 2021-03-24
0.904
best: 0.989 (UniK3D (FT, metric))
Vision Transformers for Dense Prediction arXiv:2103.13413
Depth EstimationonNYU-Depth V2
Delta < 1.25^3· uses extra data· 2021-03-24
0.994
best: 1 (HybridDepth)
Vision Transformers for Dense Prediction arXiv:2103.13413
Depth EstimationonNYU-Depth V2
RMSE· uses extra data· 2021-03-24
0.357
best: 0.013 (Defocus/DepthNet (Normalized))
Vision Transformers for Dense Prediction arXiv:2103.13413
Depth EstimationonNYU-Depth V2
absolute relative error· uses extra data· 2021-03-24
0.11
best: 0.026 (HybridDepth)
Vision Transformers for Dense Prediction arXiv:2103.13413
Depth EstimationonNYU-Depth V2
log 10· uses extra data· 2021-03-24
0.045
best: 0.059 (SC-DepthV2)
Vision Transformers for Dense Prediction arXiv:2103.13413
Depth EstimationonKITTI Eigen split
Delta < 1.25· 2021-03-24
0.959
best: 0.99 (SPIDepth)
Vision Transformers for Dense Prediction arXiv:2103.13413
Depth EstimationonKITTI Eigen split
Delta < 1.25^2· 2021-03-24
0.995
best: 0.999 (SPIDepth)
Vision Transformers for Dense Prediction arXiv:2103.13413
Depth EstimationonKITTI Eigen split
Delta < 1.25^3· 2021-03-24
0.999
best: 1 (SPIDepth)
Vision Transformers for Dense Prediction arXiv:2103.13413
Depth EstimationonKITTI Eigen split
RMSE· 2021-03-24
2.573
best: 1.394 (SPIDepth)
Vision Transformers for Dense Prediction arXiv:2103.13413
Depth EstimationonKITTI Eigen split
RMSE log· 2021-03-24
0.092
best: 0.048 (SPIDepth)
Vision Transformers for Dense Prediction arXiv:2103.13413
Depth EstimationonKITTI Eigen split
absolute relative error· 2021-03-24
0.062
best: 0.029 (SPIDepth)
Vision Transformers for Dense Prediction arXiv:2103.13413

Methodology12 results

3DonNYU-Depth V2
Delta < 1.25^2· uses extra data· 2021-03-24
0.988
best: 1 (HybridDepth)
SOTA
Vision Transformers for Dense Prediction arXiv:2103.13413
3DonNYU-Depth V2
Delta < 1.25· uses extra data· 2021-03-24
0.904
best: 0.989 (UniK3D (FT, metric))
Vision Transformers for Dense Prediction arXiv:2103.13413
3DonNYU-Depth V2
Delta < 1.25^3· uses extra data· 2021-03-24
0.994
best: 1 (HybridDepth)
Vision Transformers for Dense Prediction arXiv:2103.13413
3DonNYU-Depth V2
RMSE· uses extra data· 2021-03-24
0.357
best: 0.013 (Defocus/DepthNet (Normalized))
Vision Transformers for Dense Prediction arXiv:2103.13413
3DonNYU-Depth V2
absolute relative error· uses extra data· 2021-03-24
0.11
best: 0.026 (HybridDepth)
Vision Transformers for Dense Prediction arXiv:2103.13413
3DonNYU-Depth V2
log 10· uses extra data· 2021-03-24
0.045
best: 0.059 (SC-DepthV2)
Vision Transformers for Dense Prediction arXiv:2103.13413
3DonKITTI Eigen split
Delta < 1.25· 2021-03-24
0.959
best: 0.99 (SPIDepth)
Vision Transformers for Dense Prediction arXiv:2103.13413
3DonKITTI Eigen split
Delta < 1.25^2· 2021-03-24
0.995
best: 0.999 (SPIDepth)
Vision Transformers for Dense Prediction arXiv:2103.13413
3DonKITTI Eigen split
Delta < 1.25^3· 2021-03-24
0.999
best: 1 (SPIDepth)
Vision Transformers for Dense Prediction arXiv:2103.13413
3DonKITTI Eigen split
RMSE· 2021-03-24
2.573
best: 1.394 (SPIDepth)
Vision Transformers for Dense Prediction arXiv:2103.13413
3DonKITTI Eigen split
RMSE log· 2021-03-24
0.092
best: 0.048 (SPIDepth)
Vision Transformers for Dense Prediction arXiv:2103.13413
3DonKITTI Eigen split
absolute relative error· 2021-03-24
0.062
best: 0.029 (SPIDepth)
Vision Transformers for Dense Prediction arXiv:2103.13413

Medical4 results

Semantic SegmentationonADE20K val
Pixel Accuracy· 2021-03-24
83.11
best: 83.43 (gSwin-S)
SOTA
Vision Transformers for Dense Prediction arXiv:2103.13413
Semantic SegmentationonADE20K val
mIoU· 2021-03-24
49.02
best: 62.8 (BEiT-3)
SOTA
Vision Transformers for Dense Prediction arXiv:2103.13413
Semantic SegmentationonPASCAL Context
mIoU· 2021-03-24
60.46
best: 71.1 (VPNeXt)
Vision Transformers for Dense Prediction arXiv:2103.13413
Semantic SegmentationonADE20K
Validation mIoU· 2021-03-24
49.02
best: 63.6 (ViT-P (InternImage-H))
Vision Transformers for Dense Prediction arXiv:2103.13413

Audio4 results

10-shot image generationonADE20K val
Pixel Accuracy· 2021-03-24
83.11
best: 83.43 (gSwin-S)
SOTA
Vision Transformers for Dense Prediction arXiv:2103.13413
10-shot image generationonADE20K val
mIoU· 2021-03-24
49.02
best: 62.8 (BEiT-3)
SOTA
Vision Transformers for Dense Prediction arXiv:2103.13413
10-shot image generationonPASCAL Context
mIoU· 2021-03-24
60.46
best: 71.1 (VPNeXt)
Vision Transformers for Dense Prediction arXiv:2103.13413
10-shot image generationonADE20K
Validation mIoU· 2021-03-24
49.02
best: 63.6 (ViT-P (InternImage-H))
Vision Transformers for Dense Prediction arXiv:2103.13413