Set containment on ModelNet40 |S|=512
72AccuracyMASNET-ReLU
Evaluation results
| Method | Links | |
|---|---|---|
| MASNET-ReLU|S|=512, Class ratio=1:1, Noise (std)=0.005, m (embedding dimension)=50, d (point dimension)=32025.10 | 72 | |
| MASNET-Hat|S|=512, Class ratio=1:1, Noise (std)=0.005, m (embedding dimension)=50, d (point dimension)=32025.10 | 65 | |
| FlexSubNet|S|=512, Class ratio=1:1, Noise (std)=0.005, m (embedding dimension)=50, d (point dimension)=32025.10 | 60 | |
| DeepSets|S|=512, Class ratio=1:1, Noise (std)=0.005, m (embedding dimension)=50, d (point dimension)=32025.10 | 50 | |
| SetTransformer|S|=512, Class ratio=1:1, Noise (std)=0.005, m (embedding dimension)=50, d (point dimension)=32025.10 | 50 | |
| Neural SFE|S|=512, Class ratio=1:1, Noise (std)=0.005, m (embedding dimension)=50, d (point dimension)=32025.10 | 50 |