Object Classification on ScanObjectNN OBJ_BG v1.0
97.2AccuracyPointGPT-L
Evaluation Results
| Method | Links | |
|---|---|---|
| PointGPT-LLearning Paradigm=Self-Supervised Representation Learning, Larger pre-training dataset=true, Post-pre-training stage=true2023.05 | 97.2 | |
| PointGPT-BLearning Paradigm=Self-Supervised Representation Learning, Larger pre-training dataset=true, Post-pre-training stage=true2023.05 | 95.8 | |
| PCP-MAE#P (M)=22.1, Input=2k Points2024.08 | 95.52 | |
| ReConLearning Paradigm=Cross-modal Information and Teacher Models2023.05 | 95.4 | |
| Point-FEMAE#P (M)=27.4, Input=2k Points2024.08 | 95.18 | |
| ReCon#P (M)=43.6, Input=2k Points2024.08 | 95.18 | |
| I2P-MAE#P (M)=15.3, Input=2k Points2024.08 | 94.14 | |
| ACTLearning Paradigm=Cross-modal Information and Teacher Models2023.05 | 93.3 | |
| ACT#P (M)=22.1, Input=2k Points2024.08 | 93.29 | |
| MVTNLearning Paradigm=Supervised Learning Only2023.05 | 92.6 | |
| MVTN#P (M)=11.2, Input=20 Images2024.08 | 92.6 | |
| PointGPT-SLearning Paradigm=Self-Supervised Representation Learning, Larger pre-training dataset=false, Post-pre-training stage=false2023.05 | 91.6 | |
| PointGPT#P (M)=19.5, Input=2k Points2024.08 | 91.6 | |
| Point-M2AE#P (M)=15.3, Input=2k Points2024.08 | 91.22 | |
| Point-M2AELearning Paradigm=Self-Supervised Representation Learning2023.05 | 91.2 | |
| Joint-MAEInput=2k Points2024.08 | 90.94 | |
| TAP#P (M)=22.1, Input=2k Points2024.08 | 90.36 | |
| Point-MAE#P (M)=22.1, Input=2k Points2024.08 | 90.02 | |
| Point-MAELearning Paradigm=Self-Supervised Representation Learning2023.05 | 90 | |
| MaskPointLearning Paradigm=Self-Supervised Representation Learning2023.05 | 89.3 | |
| MaskPointInput=2k Points2024.08 | 89.3 | |
| Point-BERT#P (M)=22.1, Input=1k Points2024.08 | 87.43 | |
| Point-BERTLearning Paradigm=Self-Supervised Representation Learning2023.05 | 87.4 | |
| PointCNNLearning Paradigm=Supervised Learning Only2023.05 | 86.1 | |
| DGCNNLearning Paradigm=Supervised Learning Only2023.05 | 82.8 | |
| DGCNN#P (M)=1.8, Input=1k Points2024.08 | 82.8 | |
| PointNet++#P (M)=1.5, Input=1k Points2024.08 | 82.3 | |
| PointNetLearning Paradigm=Supervised Learning Only2023.05 | 73.3 | |
| PointNet#P (M)=3.5, Input=1k Points2024.08 | 73.3 |