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/DGCNN

DGCNN

Reported on 80 benchmarks across 13 tasks · 5 papers · 21 SOTA

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

Computer Vision70 results

Affordance Detectionon3D AffordanceNet
AIOU· 2021-03-30
0.178
SOTA
3D AffordanceNet: A Benchmark for Visual Object Affordance Understanding arXiv:2103.16397
Affordance Detectionon3D AffordanceNet
mAP· 2021-03-30
0.464
SOTA
3D AffordanceNet: A Benchmark for Visual Object Affordance Understanding arXiv:2103.16397
Affordance Detectionon3D AffordanceNet Rotate z
AIOU· 2021-03-30
0.161
SOTA
3D AffordanceNet: A Benchmark for Visual Object Affordance Understanding arXiv:2103.16397
Affordance Detectionon3D AffordanceNet Rotate z
mAP· 2021-03-30
0.448
SOTA
3D AffordanceNet: A Benchmark for Visual Object Affordance Understanding arXiv:2103.16397
Affordance Detectionon3D AffordanceNet Rotate SO(3)
AIOU· 2021-03-30
0.128
SOTA
3D AffordanceNet: A Benchmark for Visual Object Affordance Understanding arXiv:2103.16397
Affordance Detectionon3D AffordanceNet Rotate SO(3)
mAP· 2021-03-30
0.373
SOTA
3D AffordanceNet: A Benchmark for Visual Object Affordance Understanding arXiv:2103.16397
Affordance Detectionon3D AffordanceNet Partial View
AIOU· 2021-03-30
0.138
SOTA
3D AffordanceNet: A Benchmark for Visual Object Affordance Understanding arXiv:2103.16397
Affordance Detectionon3D AffordanceNet Partial View
mAP· 2021-03-30
0.422
SOTA
3D AffordanceNet: A Benchmark for Visual Object Affordance Understanding arXiv:2103.16397
Shape Representation Of 3D Point CloudsonScanObjectNN
OBJ-ONLY (OA)· 2018-01-24
86.2
best: 97.76 (PointGST)
SOTA
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
Shape Representation Of 3D Point CloudsonModelNet40
Overall Accuracy· 2018-01-24
92.9
best: 95.3 (PointGST)
SOTA
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
Shape Representation Of 3D Point CloudsonScanObjectNN
Overall Accuracy (PB_T50_RS)· 2018-01-24
78.1
best: 92.64 (Mamba3D)
SOTA
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
3D Point Cloud ClassificationonScanObjectNN
OBJ-ONLY (OA)· 2018-01-24
86.2
best: 97.76 (PointGST)
SOTA
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
3D Point Cloud ClassificationonModelNet40
Overall Accuracy· 2018-01-24
92.9
best: 95.3 (PointGST)
SOTA
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
3D Point Cloud ClassificationonScanObjectNN
Overall Accuracy (PB_T50_RS)· 2018-01-24
78.1
best: 92.64 (Mamba3D)
SOTA
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
Point Cloud SegmentationonPointCloud-C
mean Corruption Error (mCE)· 2018-01-24
1
best: 0.923 (GDANet)
SOTA
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
3D Point Cloud ReconstructiononScanObjectNN
OBJ-ONLY (OA)· 2018-01-24
86.2
best: 97.76 (PointGST)
SOTA
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
3D Point Cloud ReconstructiononModelNet40
Overall Accuracy· 2018-01-24
92.9
best: 95.3 (PointGST)
SOTA
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
3D Point Cloud ReconstructiononScanObjectNN
Overall Accuracy (PB_T50_RS)· 2018-01-24
78.1
best: 92.64 (Mamba3D)
SOTA
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
IFC Entity ClassificationonIFCNetCore
Balanced Accuracy· 2021-06-17
79.11
best: 85.54 (MVCNN)
IFCNet: A Benchmark Dataset for IFC Entity Classification arXiv:2106.09712
IFC Entity ClassificationonIFCNetCore
F1 Score· 2021-06-17
82.15
best: 86.93 (MVCNN)
IFCNet: A Benchmark Dataset for IFC Entity Classification arXiv:2106.09712
3D Semantic SegmentationonToronto-3D
OA· 2020-03-18
89
best: 95.5 (SCF-Net)
Toronto-3D: A Large-scale Mobile LiDAR Dataset for Semantic Segmentation of Urban Roadways arXiv:2003.08284
3D Semantic SegmentationonToronto-3D
mIoU· 2020-03-18
49.6
best: 73.6 (SCF-Net)
Toronto-3D: A Large-scale Mobile LiDAR Dataset for Semantic Segmentation of Urban Roadways arXiv:2003.08284
Shape Representation Of 3D Point CloudsonScanObjectNN
Mean Accuracy· 2018-01-24
73.6
best: 93.8 (GPSFormer)
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
Shape Representation Of 3D Point CloudsonScanObjectNN
OBJ-BG (OA)· 2018-01-24
82.8
best: 99.48 (PointGST)
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
Shape Representation Of 3D Point CloudsonScanObjectNN
Overall Accuracy· 2018-01-24
78.1
best: 97.2 (OmniVec2)
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
Shape Representation Of 3D Point CloudsonIntrA
F1 score (5-fold)· 2018-01-24
0.738
best: 0.936 (3DMedPT)
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
Shape Representation Of 3D Point CloudsonModelNet40
Mean Accuracy· 2018-01-24
90.2
best: 92.4 (ULIP + PointMLP)
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
Shape Representation Of 3D Point CloudsonModelNet40-C
Error Rate· 2018-01-24
0.259
best: 0.142 (OmniVec2)
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
Shape Representation Of 3D Point CloudsonModelNet40 10-way (20-shot)
Overall Accuracy· 2018-01-24
16.9
best: 96.5 (ReCon++)
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
Shape Representation Of 3D Point CloudsonModelNet40 10-way (20-shot)
Standard Deviation· 2018-01-24
1.5
best: 13.5 (PointNet)
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
Shape Representation Of 3D Point CloudsonModelNet40 5-way (10-shot)
Overall Accuracy· 2018-01-24
31.6
best: 98 (PointGPT)
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
Shape Representation Of 3D Point CloudsonModelNet40 5-way (10-shot)
Standard Deviation· 2018-01-24
9
best: 16 (PointNet++)
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
Shape Representation Of 3D Point CloudsonModelNet40 10-way (10-shot)
Overall Accuracy· 2018-01-24
19.85
best: 95 (Point-JEPA)
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
Shape Representation Of 3D Point CloudsonModelNet40 10-way (10-shot)
Standard Deviation· 2018-01-24
6.5
best: 13.5 (PointNet)
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
Shape Representation Of 3D Point CloudsonModelNet40 5-way (20-shot)
Overall Accuracy· 2018-01-24
40.8
best: 99.5 (ReCon++)
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
Shape Representation Of 3D Point CloudsonModelNet40 5-way (20-shot)
Standard Deviation· 2018-01-24
14.6
best: 15.5 (PointNet)
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
Shape Representation Of 3D Point CloudsonScanObjectNN
GFLOPs· 2018-01-24
2.4
best: 45 (PCM)
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
Shape Representation Of 3D Point CloudsonScanObjectNN
Number of params (M)· 2018-01-24
1.8
best: 34.2 (PCM)
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
3D Point Cloud ClassificationonScanObjectNN
Mean Accuracy· 2018-01-24
73.6
best: 93.8 (GPSFormer)
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
3D Point Cloud ClassificationonScanObjectNN
OBJ-BG (OA)· 2018-01-24
82.8
best: 99.48 (PointGST)
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
3D Point Cloud ClassificationonScanObjectNN
Overall Accuracy· 2018-01-24
78.1
best: 97.2 (OmniVec2)
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
3D Point Cloud ClassificationonIntrA
F1 score (5-fold)· 2018-01-24
0.738
best: 0.936 (3DMedPT)
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
3D Point Cloud ClassificationonModelNet40
Mean Accuracy· 2018-01-24
90.2
best: 92.4 (ULIP + PointMLP)
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
3D Point Cloud ClassificationonModelNet40-C
Error Rate· 2018-01-24
0.259
best: 0.142 (OmniVec2)
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
3D Point Cloud ClassificationonModelNet40 10-way (20-shot)
Overall Accuracy· 2018-01-24
16.9
best: 96.5 (ReCon++)
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
3D Point Cloud ClassificationonModelNet40 10-way (20-shot)
Standard Deviation· 2018-01-24
1.5
best: 13.5 (PointNet)
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
3D Point Cloud ClassificationonModelNet40 5-way (10-shot)
Overall Accuracy· 2018-01-24
31.6
best: 98 (PointGPT)
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
3D Point Cloud ClassificationonModelNet40 5-way (10-shot)
Standard Deviation· 2018-01-24
9
best: 16 (PointNet++)
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
3D Point Cloud ClassificationonModelNet40 10-way (10-shot)
Overall Accuracy· 2018-01-24
19.85
best: 95 (Point-JEPA)
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
3D Point Cloud ClassificationonModelNet40 10-way (10-shot)
Standard Deviation· 2018-01-24
6.5
best: 13.5 (PointNet)
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
3D Point Cloud ClassificationonModelNet40 5-way (20-shot)
Overall Accuracy· 2018-01-24
40.8
best: 99.5 (ReCon++)
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
3D Point Cloud ClassificationonModelNet40 5-way (20-shot)
Standard Deviation· 2018-01-24
14.6
best: 15.5 (PointNet)
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
3D Point Cloud ClassificationonScanObjectNN
GFLOPs· 2018-01-24
2.4
best: 45 (PCM)
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
3D Point Cloud ClassificationonScanObjectNN
Number of params (M)· 2018-01-24
1.8
best: 34.2 (PCM)
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
3D Point Cloud ReconstructiononScanObjectNN
Mean Accuracy· 2018-01-24
73.6
best: 93.8 (GPSFormer)
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
3D Point Cloud ReconstructiononScanObjectNN
OBJ-BG (OA)· 2018-01-24
82.8
best: 99.48 (PointGST)
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
3D Point Cloud ReconstructiononScanObjectNN
Overall Accuracy· 2018-01-24
78.1
best: 97.2 (OmniVec2)
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
3D Point Cloud ReconstructiononIntrA
F1 score (5-fold)· 2018-01-24
0.738
best: 0.936 (3DMedPT)
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
3D Point Cloud ReconstructiononModelNet40
Mean Accuracy· 2018-01-24
90.2
best: 92.4 (ULIP + PointMLP)
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
3D Point Cloud ReconstructiononModelNet40-C
Error Rate· 2018-01-24
0.259
best: 0.142 (OmniVec2)
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
3D Point Cloud ReconstructiononModelNet40 10-way (20-shot)
Overall Accuracy· 2018-01-24
16.9
best: 96.5 (ReCon++)
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
3D Point Cloud ReconstructiononModelNet40 10-way (20-shot)
Standard Deviation· 2018-01-24
1.5
best: 13.5 (PointNet)
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
3D Point Cloud ReconstructiononModelNet40 5-way (10-shot)
Overall Accuracy· 2018-01-24
31.6
best: 98 (PointGPT)
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
3D Point Cloud ReconstructiononModelNet40 5-way (10-shot)
Standard Deviation· 2018-01-24
9
best: 16 (PointNet++)
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
3D Point Cloud ReconstructiononModelNet40 10-way (10-shot)
Overall Accuracy· 2018-01-24
19.85
best: 95 (Point-JEPA)
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
3D Point Cloud ReconstructiononModelNet40 10-way (10-shot)
Standard Deviation· 2018-01-24
6.5
best: 13.5 (PointNet)
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
3D Point Cloud ReconstructiononModelNet40 5-way (20-shot)
Overall Accuracy· 2018-01-24
40.8
best: 99.5 (ReCon++)
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
3D Point Cloud ReconstructiononModelNet40 5-way (20-shot)
Standard Deviation· 2018-01-24
14.6
best: 15.5 (PointNet)
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
3D Point Cloud ReconstructiononScanObjectNN
GFLOPs· 2018-01-24
2.4
best: 45 (PCM)
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
3D Point Cloud ReconstructiononScanObjectNN
Number of params (M)· 2018-01-24
1.8
best: 34.2 (PCM)
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829

Medical3 results

Semantic SegmentationonToronto-3D
OA· 2020-03-18
89
best: 95.5 (SCF-Net)
Toronto-3D: A Large-scale Mobile LiDAR Dataset for Semantic Segmentation of Urban Roadways arXiv:2003.08284
Semantic SegmentationonToronto-3D
mIoU· 2020-03-18
49.6
best: 73.6 (SCF-Net)
Toronto-3D: A Large-scale Mobile LiDAR Dataset for Semantic Segmentation of Urban Roadways arXiv:2003.08284
Semantic SegmentationonShapeNet-Part
Instance Average IoU· 2018-01-24
85.2
best: 89.1 (GeomGCNN)
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829

Audio3 results

10-shot image generationonToronto-3D
OA· 2020-03-18
89
best: 95.5 (SCF-Net)
Toronto-3D: A Large-scale Mobile LiDAR Dataset for Semantic Segmentation of Urban Roadways arXiv:2003.08284
10-shot image generationonToronto-3D
mIoU· 2020-03-18
49.6
best: 73.6 (SCF-Net)
Toronto-3D: A Large-scale Mobile LiDAR Dataset for Semantic Segmentation of Urban Roadways arXiv:2003.08284
10-shot image generationonShapeNet-Part
Instance Average IoU· 2018-01-24
85.2
best: 89.1 (GeomGCNN)
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829

Graphs2 results

Point Cloud ClassificationonPointCloud-C
mean Corruption Error (mCE)· 2018-01-24
1
best: 0.455 (BeyondRPC)
SOTA
Dynamic Graph CNN for Learning on Point Clouds arXiv:1801.07829
Graph ClassificationonAIDS
Accuracy· 2017-12-10
65.1
best: 84.3 (FIT-GNN)
SOTA
DGCNN: Disordered Graph Convolutional Neural Network Based on the Gaussian Mixture Model arXiv:1712.03563

Methodology2 results

ClassificationonAIDS
Accuracy· 2017-12-10
65.1
best: 84.3 (FIT-GNN)
SOTA
DGCNN: Disordered Graph Convolutional Neural Network Based on the Gaussian Mixture Model arXiv:1712.03563
Electroencephalogram (EEG)onSEED-IV
Accuracy
69.88
best: 74.35 (BiHDM)