Few-Shot Learning on ModelNet40
97.1Acc (5w10s)MOST
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| MOSTBackbone=ReCon [38], #P (M)=1.3, #F (G)=4.8, Training Strategy=with Pre-Training (Parameter-Efficient Fine-Tuning)2025.03 | 97.1 | 98.9 | 93.1 | 95.6 | |
| MOSTBackbone=Mamba3D [20], #P (M)=1.2, #F (G)=3.9, Training Strategy=with Pre-Training (Parameter-Efficient Fine-Tuning)2025.03 | 96.8 | 98.3 | 93 | 95.4 | |
| MOST (Mamba3D)#P (M)=5.1, #F (G)=2.6, Training Strategy=Supervised Learning Only (Sparse Training)2025.03 | 94.4 | 96 | 88.3 | 89.4 | |
| MOST (Transformer)#P (M)=5.6, #F (G)=2.8, Training Strategy=Supervised Learning Only (Sparse Training)2025.03 | 92 | 95.4 | 84.3 | 88.8 |