Few-shot Classification on ModelNet40 (test) (10-way)
94.110-shot AccPointGPT-L
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| PointGPT-LModel Size=Large, Learning Type=Self-Supervised Representation Learning, Larger Pre-training=true, Post-pre-training stage excluded=true2023.05 | 94.1 | 96.1 | |
| PointGPT-BModel Size=Base, Learning Type=Self-Supervised Representation Learning, Larger Pre-training=true, Post-pre-training stage excluded=true2023.05 | 93.5 | 95.8 | |
| ACTLearning Type=Cross-modal information and teacher models2023.05 | 93.3 | 95.6 | |
| ReConLearning Type=Cross-modal information and teacher models2023.05 | 93.3 | 95.8 | |
| Point-MAELearning Type=Self-Supervised Representation Learning2023.05 | 92.6 | 95 | |
| PointGPT-SModel Size=Small, Learning Type=Self-Supervised Representation Learning, Larger Pre-training=false, Post-pre-training stage excluded=false2023.05 | 92.6 | 95.2 | |
| Point-M2AELearning Type=Self-Supervised Representation Learning2023.05 | 92.3 | 95 | |
| MaskPointLearning Type=Self-Supervised Representation Learning2023.05 | 91.4 | 93.4 | |
| Point-BERTLearning Type=Self-Supervised Representation Learning2023.05 | 91 | 92.7 | |
| OcCoLearning Type=Supervised2023.05 | 82.9 | 86.5 | |
| DGCNNLearning Type=Supervised2023.05 | 19.9 | 16.9 |