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/DSN

DSN

Reported on 15 benchmarks across 7 tasks · 3 papers · 6 SOTA

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

Computer Vision11 results

Depth CompletiononKITTI Depth Completion Eigen Split
REL· uses extra data· 2020-10-13
0.019
SOTA
On Deep Learning Techniques to Boost Monocular Depth Estimation for Autonomous Navigation arXiv:2010.06626
Depth CompletiononKITTI Depth Completion Eigen Split
RMSE· uses extra data· 2020-10-13
1.588
SOTA
On Deep Learning Techniques to Boost Monocular Depth Estimation for Autonomous Navigation arXiv:2010.06626
Surface Normals EstimationonNYU-Depth V2 Surface Normals
RMSE· uses extra data· 2020-10-13
12.2
SOTA
On Deep Learning Techniques to Boost Monocular Depth Estimation for Autonomous Navigation arXiv:2010.06626
Image ClassificationonCIFAR-10
Percentage correct· 2014-09-18
91.8
best: 99.5 (ViT-H/14)
SOTA
Deeply-Supervised Nets arXiv:1409.5185
Image ClassificationonCIFAR-100
Percentage correct· 2014-09-18
65.4
best: 96.08 (EffNet-L2 (SAM))
SOTA
Deeply-Supervised Nets arXiv:1409.5185
Image ClassificationonSVHN
Percentage error· 2014-09-18
1.9
best: 1 (E2E-M3)
SOTA
Deeply-Supervised Nets arXiv:1409.5185
Depth EstimationonNYU-Depth V2
RMSE· uses extra data· 2020-10-13
0.429
best: 0.013 (Defocus/DepthNet (Normalized))
On Deep Learning Techniques to Boost Monocular Depth Estimation for Autonomous Navigation arXiv:2010.06626
Depth EstimationonKITTI Eigen split
absolute relative error· 2020-10-13
0.075
best: 0.029 (SPIDepth)
On Deep Learning Techniques to Boost Monocular Depth Estimation for Autonomous Navigation arXiv:2010.06626
Depth CompletiononNYU-Depth V2
REL· uses extra data· 2020-10-13
0.012
On Deep Learning Techniques to Boost Monocular Depth Estimation for Autonomous Navigation arXiv:2010.06626
Depth CompletiononNYU-Depth V2
RMSE· uses extra data· 2020-10-13
0.102
best: 0.092 (NLSPN)
On Deep Learning Techniques to Boost Monocular Depth Estimation for Autonomous Navigation arXiv:2010.06626
Image ClassificationonMNIST
Percentage error· 2014-09-18
0.4
best: 0.13 (Branching/Merging CNN + Homogeneous Vector Capsules)
Deeply-Supervised Nets arXiv:1409.5185

Methodology2 results

3DonNYU-Depth V2
RMSE· uses extra data· 2020-10-13
0.429
best: 0.013 (Defocus/DepthNet (Normalized))
On Deep Learning Techniques to Boost Monocular Depth Estimation for Autonomous Navigation arXiv:2010.06626
3DonKITTI Eigen split
absolute relative error· 2020-10-13
0.075
best: 0.029 (SPIDepth)
On Deep Learning Techniques to Boost Monocular Depth Estimation for Autonomous Navigation arXiv:2010.06626

Robots1 result

Activity RecognitiononActivityNet
mAP· 2020-06-28
87.9
best: 96.9 (Text4Vis (w/ ViT-L))
Dynamic Sampling Networks for Efficient Action Recognition in Videos arXiv:2006.15560

Time Series1 result

Action RecognitiononActivityNet
mAP· 2020-06-28
87.9
best: 96.9 (Text4Vis (w/ ViT-L))
Dynamic Sampling Networks for Efficient Action Recognition in Videos arXiv:2006.15560