3D Object Classification on ScanObjectNN 46 (test)
58.5Top-1 AccTAMM
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| TAMMPre-Training Dataset=Ensembled, Model Architecture=SparseConv, Zero-shot Protocol=true2024.02 | 58.5 | 81.3 | 89.5 | |
| TAMMPre-Training Dataset=ShapeNet, Model Architecture=SparseConv, Zero-shot Protocol=true2024.02 | 57.9 | 75.3 | 83.1 | |
| TAMMPre-Training Dataset=Ensembled (no LVIS), Model Architecture=SparseConv, Zero-shot Protocol=true2024.02 | 57.5 | 81.3 | 90 | |
| TAMMPre-Training Dataset=Ensembled (no LVIS), Model Architecture=Point-BERT, Zero-shot Protocol=true2024.02 | 56.7 | 78.3 | 86.1 | |
| OpenShapePre-Training Dataset=Ensembled, Model Architecture=SparseConv, Zero-shot Protocol=true2024.02 | 56.7 | 78.9 | 88.6 | |
| TAMMPre-Training Dataset=Ensembled, Model Architecture=Point-BERT, Zero-shot Protocol=true2024.02 | 55.7 | 80.7 | 88.9 | |
| OpenShapePre-Training Dataset=Ensembled (no LVIS), Model Architecture=SparseConv, Zero-shot Protocol=true2024.02 | 54.9 | 76.8 | 87 | |
| TAMMPre-Training Dataset=ShapeNet, Model Architecture=Point-BERT, Zero-shot Protocol=true2024.02 | 54.8 | 74.5 | 83.3 | |
| OpenShapePre-Training Dataset=ShapeNet, Model Architecture=SparseConv, Zero-shot Protocol=true2024.02 | 52.7 | 72.7 | 83.6 | |
| OpenShapePre-Training Dataset=Ensembled, Model Architecture=Point-BERT, Zero-shot Protocol=true2024.02 | 52.2 | 79.7 | 88.7 | |
| ULIPPre-Training Dataset=Ensembled, Model Architecture=Point-BERT, Zero-shot Protocol=true2024.02 | 51.6 | 72.5 | 82.3 | |
| ULIPPre-Training Dataset=ShapeNet, Model Architecture=Point-BERT, Zero-shot Protocol=true2024.02 | 51.5 | 71.1 | 80.2 | |
| OpenShapePre-Training Dataset=ShapeNet, Model Architecture=Point-BERT, Zero-shot Protocol=true2024.02 | 51.3 | 69.4 | 78.4 | |
| OpenShapePre-Training Dataset=Ensembled (no LVIS), Model Architecture=Point-BERT, Zero-shot Protocol=true2024.02 | 47.2 | 72.4 | 84.7 | |
| ULIPPre-Training Dataset=Ensembled (no LVIS), Model Architecture=Point-BERT, Zero-shot Protocol=true2024.02 | 46 | 66.1 | 76.4 | |
| ReConPre-Training Dataset=None, Model Architecture=Transformer, Zero-shot Protocol=true2024.02 | 42.3 | 62.5 | 75.6 | |
| PointCLIP v2Pre-Training Dataset=None, Model Architecture=PointCLIP v2, Zero-shot Protocol=true2024.02 | 42.2 | 63.3 | 74.5 | |
| CLIP2PointPre-Training Dataset=None, Model Architecture=ViT-B/32, Zero-shot Protocol=true2024.02 | 25.5 | 44.6 | 59.4 | |
| PointCLIPPre-Training Dataset=None, Model Architecture=PointCLIP, Zero-shot Protocol=true2024.02 | 10.5 | 20.8 | 30.6 |