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/DeepGCN

DeepGCN

Reported on 16 benchmarks across 7 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 Vision7 results

Shape Representation Of 3D Point CloudsonModelNet40
Overall Accuracy· 2019-10-15
93.6
best: 95.3 (PointGST)
SOTA
DeepGCNs: Making GCNs Go as Deep as CNNs arXiv:1910.06849
3D Semantic SegmentationonPartNet
mIOU· 2019-10-15
45.1
best: 62.1 (CSN)
SOTA
DeepGCNs: Making GCNs Go as Deep as CNNs arXiv:1910.06849
3D Point Cloud ClassificationonModelNet40
Overall Accuracy· 2019-10-15
93.6
best: 95.3 (PointGST)
SOTA
DeepGCNs: Making GCNs Go as Deep as CNNs arXiv:1910.06849
3D Point Cloud ReconstructiononModelNet40
Overall Accuracy· 2019-10-15
93.6
best: 95.3 (PointGST)
SOTA
DeepGCNs: Making GCNs Go as Deep as CNNs arXiv:1910.06849
Shape Representation Of 3D Point CloudsonModelNet40
Mean Accuracy· 2019-10-15
90.9
best: 92.4 (ULIP + PointMLP)
DeepGCNs: Making GCNs Go as Deep as CNNs arXiv:1910.06849
3D Point Cloud ClassificationonModelNet40
Mean Accuracy· 2019-10-15
90.9
best: 92.4 (ULIP + PointMLP)
DeepGCNs: Making GCNs Go as Deep as CNNs arXiv:1910.06849
3D Point Cloud ReconstructiononModelNet40
Mean Accuracy· 2019-10-15
90.9
best: 92.4 (ULIP + PointMLP)
DeepGCNs: Making GCNs Go as Deep as CNNs arXiv:1910.06849

Medical4 results

Semantic SegmentationonPartNet
mIOU· 2019-10-15
45.1
best: 62.1 (CSN)
SOTA
DeepGCNs: Making GCNs Go as Deep as CNNs arXiv:1910.06849
Semantic SegmentationonS3DIS Area5
mIoU· 2019-10-15
52.49
best: 76 (Sonata + PTv3)
DeepGCNs: Making GCNs Go as Deep as CNNs arXiv:1910.06849
Semantic SegmentationonS3DIS
Mean IoU· 2019-10-15
60
best: 82.3 (Sonata + PTv3)
DeepGCNs: Making GCNs Go as Deep as CNNs arXiv:1910.06849
Semantic SegmentationonS3DIS
oAcc· 2019-10-15
85.9
best: 93.3 (Sonata + PTv3)
DeepGCNs: Making GCNs Go as Deep as CNNs arXiv:1910.06849

Audio4 results

10-shot image generationonPartNet
mIOU· 2019-10-15
45.1
best: 62.1 (CSN)
SOTA
DeepGCNs: Making GCNs Go as Deep as CNNs arXiv:1910.06849
10-shot image generationonS3DIS Area5
mIoU· 2019-10-15
52.49
best: 76 (Sonata + PTv3)
DeepGCNs: Making GCNs Go as Deep as CNNs arXiv:1910.06849
10-shot image generationonS3DIS
Mean IoU· 2019-10-15
60
best: 82.3 (Sonata + PTv3)
DeepGCNs: Making GCNs Go as Deep as CNNs arXiv:1910.06849
10-shot image generationonS3DIS
oAcc· 2019-10-15
85.9
best: 93.3 (Sonata + PTv3)
DeepGCNs: Making GCNs Go as Deep as CNNs arXiv:1910.06849

Graphs1 result

Node Property Predictiononogbn-proteins
Number of params
2374456
best: 664233700 (LD+GAT)