3D Object Classification on ModelNet40 8k P
94.3AccuracyIAE (M2AE)
Evaluation results
| Method | Links | |
|---|---|---|
| IAE (M2AE)#Params(M)=15.3, GFLOPS=3.6, Evaluation Protocol=FULL SSL2025.12 | 94.3 | |
| IAE (DGCNN)#Params(M)=1.8, GFLOPS=2.4, Evaluation Protocol=FULL SSL2025.12 | 94.2 | |
| IAE (M2AE)#Params(M)=15.3, GFLOPS=3.6, Evaluation Protocol=FULL SSL, pre-training mesh=w/o mesh2025.12 | 94.2 | |
| Point-MAE#Params(M)=22.1, GFLOPS=4.8, Evaluation Protocol=FULL SSL2025.12 | 94 | |
| Point-BERT#Params(M)=22.1, GFLOPS=4.8, Evaluation Protocol=FULL SSL2025.12 | 93.8 | |
| DGCNN#Params(M)=1.8, GFLOPS=2.4, Evaluation Protocol=FULL SSL2025.12 | 93.1 | |
| PointNet++#Params(M)=1.5, GFLOPS=1.7, Evaluation Protocol=Supervised2025.12 | 91.9 | |
| Transformer#Params(M)=22.1, GFLOPS=4.8, Evaluation Protocol=FULL SSL2025.12 | 91.8 | |
| PointNet#Params(M)=3.5, GFLOPS=0.5, Evaluation Protocol=Supervised2025.12 | 90.8 |