3D Point Cloud Classification on ModelNet40 55
0.9623AccuracyMOSTb=8
Evaluation results
| Method | Links | |
|---|---|---|
| MOSTb=8Backbone=PointGPT, 3D-designed (3D)=true, No inference overhead (NO)=true, Trainable Parameters (#P)=8.0M2025.03 | 0.9623 | |
| MOSTb=16Backbone=PointGPT, 3D-designed (3D)=true, No inference overhead (NO)=true, Trainable Parameters (#P)=4.4M2025.03 | 0.9611 | |
| MOSTb=32Backbone=PointGPT, 3D-designed (3D)=true, No inference overhead (NO)=true, Trainable Parameters (#P)=2.5M2025.03 | 0.9595 | |
| MOSTb=8Backbone=Point-MAE, 3D-designed (3D)=true, No inference overhead (NO)=true, Trainable Parameters (#P)=2.3M2025.03 | 0.9477 | |
| MOSTb=16Backbone=Point-MAE, 3D-designed (3D)=true, No inference overhead (NO)=true, Trainable Parameters (#P)=1.3M2025.03 | 0.9449 | |
| MOSTb=32Backbone=Point-MAE, 3D-designed (3D)=true, No inference overhead (NO)=true, Trainable Parameters (#P)=0.8M2025.03 | 0.9404 | |
| Full FTBackbone=Point-MAE, Trainable Parameters (#P)=22.1M2025.03 | 0.938 | |
| LoRABackbone=PointGPT, 3D-designed (3D)=false, No inference overhead (NO)=true, Trainable Parameters (#P)=2.4M2025.03 | 0.9295 |