3D Object Classification on ScanObjectNN OBJ_ONLY v1
0.9329Overall Accuracy (Highest)RECON
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| RECONReference=ICML 23, Params. (M)=44.3, Training Protocol=Self-Supervised Representation Learning (FULL)2024.08 | 0.9329 | — | — | |
| PPTReference=ACMMM 25, Params. (M)=1.1, Baseline=RECON, Training Protocol=Parameter-Efficient Supervised Fine-tuning2024.08 | 0.9328 | 0.9323 | — | |
| RECON (Baseline)Reference=ICML 23, Params. (M)=22.1, Training Protocol=Parameter-Efficient Supervised Fine-tuning2024.08 | 0.9277 | — | — | |
| IDPTReference=ICCV 23, Params. (M)=1.7, Baseline=Point-MAE, Training Protocol=Parameter-Efficient Supervised Fine-tuning2024.08 | 0.926 | 0.9133 | — | |
| PPTReference=ACMMM 25, Params. (M)=1.1, Baseline=Point-MAE, Training Protocol=Parameter-Efficient Supervised Fine-tuning2024.08 | 0.926 | 0.9243 | — | |
| DAPTReference=CVPR 24, Params. (M)=1.1, Baseline=RECON, Training Protocol=Parameter-Efficient Supervised Fine-tuning2024.08 | 0.9243 | 0.9163 | — | |
| ACTReference=ICLR 23, Params. (M)=22.1, Training Protocol=Self-Supervised Representation Learning (FULL)2024.08 | 0.9191 | — | — | |
| VPPReference=NeurIPS 23, Params. (M)=22.1, Training Protocol=Self-Supervised Representation Learning (FULL)2024.08 | 0.9191 | — | — | |
| DAPTReference=CVPR 24, Params. (M)=1.1, Baseline=Point-MAE, Training Protocol=Parameter-Efficient Supervised Fine-tuning2024.08 | 0.9191 | 0.9131 | — | |
| IDPTReference=ICCV 23, Params. (M)=1.7, Baseline=RECON, Training Protocol=Parameter-Efficient Supervised Fine-tuning2024.08 | 0.9174 | 0.9137 | — | |
| I2P-MAEReference=CVPR 23, Params. (M)=15.3, Training Protocol=Self-Supervised Representation Learning (FULL)2024.08 | 0.9157 | — | — | |
| Point-M2AEReference=NeurIPS 22, Params. (M)=15.3, Training Protocol=Self-Supervised Representation Learning (FULL)2024.08 | 0.8881 | — | — | |
| Point-MAEReference=ECCV 22, Params. (M)=22.1, Training Protocol=Self-Supervised Representation Learning (FULL)2024.08 | 0.8829 | — | — | |
| Point-MAE (Baseline)Reference=ECCV 22, Params. (M)=22.1, Training Protocol=Parameter-Efficient Supervised Fine-tuning2024.08 | 0.8829 | — | — | |
| Point-BERTReference=CVPR 22, Params. (M)=22.1, Training Protocol=Self-Supervised Representation Learning (FULL)2024.08 | 0.8812 | — | — | |
| DGCNNReference=TOG 19, Params. (M)=1.8, Training Protocol=Supervised Learning Only2024.08 | 0.862 | — | — | |
| OcCoReference=ICCV 21, Params. (M)=22.1, Training Protocol=Self-Supervised Representation Learning (FULL)2024.08 | 0.8554 | — | — | |
| PointNet++Reference=NeurIPS 17, Params. (M)=1.5, Training Protocol=Supervised Learning Only2024.08 | 0.843 | — | — | |
| PointNetReference=CVPR 17, Params. (M)=3.5, Training Protocol=Supervised Learning Only2024.08 | 0.792 | — | — | |
| ACTTransfer Protocol=FULL, #Params(M)=22.1, DA=false, Training Augmentation=None2022.12 | — | — | 89.16 | |
| ACTTransfer Protocol=FULL, #Params(M)=22.1, DA=true, Training Augmentation=Rotation2022.12 | — | — | 91.91 | |
| DGCNNTransfer Protocol=Supervised Learning Only, #Params(M)=1.8, DA=true2022.12 | — | — | 86.2 | |
| MaskPointTransfer Protocol=FULL, #Params(M)=22.1, DA=true2022.12 | — | — | 88.1 | |
| OcCoTransfer Protocol=FULL, #Params(M)=22.1, DA=true2022.12 | — | — | 85.54 | |
| Point-BERTTransfer Protocol=FULL, #Params(M)=22.1, DA=true2022.12 | — | — | 88.12 | |
| Point-MAETransfer Protocol=FULL, #Params(M)=22.1, DA=true2022.12 | — | — | 88.29 | |
| PointCNNTransfer Protocol=Supervised Learning Only, #Params(M)=0.6, DA=true2022.12 | — | — | 85.5 | |
| PointNetTransfer Protocol=Supervised Learning Only, #Params(M)=3.5, DA=true2022.12 | — | — | 79.2 | |
| PointNet++Transfer Protocol=Supervised Learning Only, #Params(M)=1.5, DA=true2022.12 | — | — | 84.3 | |
| SpiderCNNTransfer Protocol=Supervised Learning Only, DA=true2022.12 | — | — | 79.5 | |
| TransformerTransfer Protocol=FULL, #Params(M)=22.1, DA=true2022.12 | — | — | 80.55 |