Object Classification on ModelNet40 8k points
94.9AccuracyPointGPT-L
Evaluation Results
| Method | Links | |
|---|---|---|
| PointGPT-LLearning Paradigm=Self-Supervised Representation Learning, Larger pre-training dataset=true, Post-pre-training stage=true2023.05 | 94.9 | |
| PointMLP+ULIPLearning Paradigm=Cross-modal Information and Teacher Models2023.05 | 94.7 | |
| ReConLearning Paradigm=Cross-modal Information and Teacher Models2023.05 | 94.7 | |
| PointGPT-BLearning Paradigm=Self-Supervised Representation Learning, Larger pre-training dataset=true, Post-pre-training stage=true2023.05 | 94.6 | |
| PointGPT-SLearning Paradigm=Self-Supervised Representation Learning, Larger pre-training dataset=false, Post-pre-training stage=false2023.05 | 94.2 | |
| Point-MAELearning Paradigm=Self-Supervised Representation Learning2023.05 | 94 | |
| ACTLearning Paradigm=Cross-modal Information and Teacher Models2023.05 | 94 | |
| Point-BERTLearning Paradigm=Self-Supervised Representation Learning2023.05 | 93.8 | |
| PointNetLearning Paradigm=Supervised Learning Only2023.05 | 90.8 |