3D Object Classification on Objaverse LVIS 10 (test)
50.7Top-1 AccTAMM
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| TAMMPre-Training Dataset=Ensembled, Model Architecture=Point-BERT, Zero-shot Protocol=true2024.02 | 50.7 | 73.2 | 80.6 | |
| OpenShapePre-Training Dataset=Ensembled, Model Architecture=Point-BERT, Zero-shot Protocol=true2024.02 | 46.8 | 69.1 | 77 | |
| TAMMPre-Training Dataset=Ensembled, Model Architecture=SparseConv, Zero-shot Protocol=true2024.02 | 43.8 | 66.2 | 74.1 | |
| OpenShapePre-Training Dataset=Ensembled, Model Architecture=SparseConv, Zero-shot Protocol=true2024.02 | 43.4 | 64.8 | 72.4 | |
| TAMMPre-Training Dataset=Ensembled (no LVIS), Model Architecture=Point-BERT, Zero-shot Protocol=true2024.02 | 42 | 63.6 | 71.7 | |
| TAMMPre-Training Dataset=Ensembled (no LVIS), Model Architecture=SparseConv, Zero-shot Protocol=true2024.02 | 39.8 | 62 | 70.4 | |
| OpenShapePre-Training Dataset=Ensembled (no LVIS), Model Architecture=Point-BERT, Zero-shot Protocol=true2024.02 | 39.1 | 60.8 | 68.9 | |
| OpenShapePre-Training Dataset=Ensembled (no LVIS), Model Architecture=SparseConv, Zero-shot Protocol=true2024.02 | 37 | 58.4 | 66.9 | |
| ULIPPre-Training Dataset=Ensembled, Model Architecture=Point-BERT, Zero-shot Protocol=true2024.02 | 26.8 | 44.8 | 52.6 | |
| ULIPPre-Training Dataset=Ensembled (no LVIS), Model Architecture=Point-BERT, Zero-shot Protocol=true2024.02 | 21.4 | 38.1 | 46 | |
| TAMMPre-Training Dataset=ShapeNet, Model Architecture=Point-BERT, Zero-shot Protocol=true2024.02 | 13.7 | 24.2 | 29.2 | |
| TAMMPre-Training Dataset=ShapeNet, Model Architecture=SparseConv, Zero-shot Protocol=true2024.02 | 13.6 | 24.2 | 29.3 | |
| OpenShapePre-Training Dataset=ShapeNet, Model Architecture=SparseConv, Zero-shot Protocol=true2024.02 | 11.6 | 21.8 | 27.1 | |
| OpenShapePre-Training Dataset=ShapeNet, Model Architecture=Point-BERT, Zero-shot Protocol=true2024.02 | 10.8 | 20.2 | 25 | |
| ULIPPre-Training Dataset=ShapeNet, Model Architecture=Point-BERT, Zero-shot Protocol=true2024.02 | 6.2 | 13.6 | 17.9 | |
| PointCLIP v2Pre-Training Dataset=None, Model Architecture=PointCLIP v2, Zero-shot Protocol=true2024.02 | 4.7 | 9.5 | 12.9 | |
| CLIP2PointPre-Training Dataset=None, Model Architecture=ViT-B/32, Zero-shot Protocol=true2024.02 | 2.7 | 5.8 | 7.9 | |
| PointCLIPPre-Training Dataset=None, Model Architecture=PointCLIP, Zero-shot Protocol=true2024.02 | 1.9 | 4.1 | 5.8 | |
| ReConPre-Training Dataset=None, Model Architecture=Transformer, Zero-shot Protocol=true2024.02 | 1.1 | 2.7 | 3.7 |