3D Object Classification on ScanObjectNN OBJ_BG v1
95.18Overall AccuracyRECON
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| RECONReference=ICML 23, Params. (M)=44.3, Training Protocol=Self-Supervised Representation Learning (FULL)2024.08 | 95.18 | — | |
| PPTReference=ACMMM 25, Params. (M)=1.1, Baseline=RECON, Training Protocol=Parameter-Efficient Supervised Fine-tuning2024.08 | 95.01 | 94.09 | |
| RECON (Baseline)Reference=ICML 23, Params. (M)=22.1, Training Protocol=Parameter-Efficient Supervised Fine-tuning2024.08 | 94.32 | — | |
| I2P-MAEReference=CVPR 23, Params. (M)=15.3, Training Protocol=Self-Supervised Representation Learning (FULL)2024.08 | 94.15 | — | |
| PPTReference=ACMMM 25, Params. (M)=1.1, Baseline=Point-MAE, Training Protocol=Parameter-Efficient Supervised Fine-tuning2024.08 | 93.63 | 92.99 | |
| DAPTReference=CVPR 24, Params. (M)=1.1, Baseline=RECON, Training Protocol=Parameter-Efficient Supervised Fine-tuning2024.08 | 93.63 | 93.12 | |
| IDPTReference=ICCV 23, Params. (M)=1.7, Baseline=RECON, Training Protocol=Parameter-Efficient Supervised Fine-tuning2024.08 | 93.46 | 92.88 | |
| ACTReference=ICLR 23, Params. (M)=22.1, Training Protocol=Self-Supervised Representation Learning (FULL)2024.08 | 93.29 | — | |
| VPPReference=NeurIPS 23, Params. (M)=22.1, Training Protocol=Self-Supervised Representation Learning (FULL)2024.08 | 93.11 | — | |
| IDPTReference=ICCV 23, Params. (M)=1.7, Baseline=Point-MAE, Training Protocol=Parameter-Efficient Supervised Fine-tuning2024.08 | 92.94 | 92.38 | |
| DAPTReference=CVPR 24, Params. (M)=1.1, Baseline=Point-MAE, Training Protocol=Parameter-Efficient Supervised Fine-tuning2024.08 | 92.43 | 91.61 | |
| Point-M2AEReference=NeurIPS 22, Params. (M)=15.3, Training Protocol=Self-Supervised Representation Learning (FULL)2024.08 | 91.22 | — | |
| Point-MAEReference=ECCV 22, Params. (M)=22.1, Training Protocol=Self-Supervised Representation Learning (FULL)2024.08 | 90.02 | — | |
| Point-MAE (Baseline)Reference=ECCV 22, Params. (M)=22.1, Training Protocol=Parameter-Efficient Supervised Fine-tuning2024.08 | 90.02 | — | |
| Point-BERTReference=CVPR 22, Params. (M)=22.1, Training Protocol=Self-Supervised Representation Learning (FULL)2024.08 | 87.43 | — | |
| Point-BERT2021.11 | 87.43 | — | |
| PointCNN2021.11 | 86.1 | — | |
| OcCoReference=ICCV 21, Params. (M)=22.1, Training Protocol=Self-Supervised Representation Learning (FULL)2024.08 | 84.85 | — | |
| Transformer-OcCo2021.11 | 84.85 | — | |
| DGCNNReference=TOG 19, Params. (M)=1.8, Training Protocol=Supervised Learning Only2024.08 | 82.8 | — | |
| DGCNN2021.11 | 82.8 | — | |
| PointNet++Reference=NeurIPS 17, Params. (M)=1.5, Training Protocol=Supervised Learning Only2024.08 | 82.3 | — | |
| PointNet++2021.11 | 82.3 | — | |
| Transformer2021.11 | 79.86 | — | |
| SpiderCNN2021.11 | 77.1 | — | |
| PointNetReference=CVPR 17, Params. (M)=3.5, Training Protocol=Supervised Learning Only2024.08 | 73.3 | — | |
| PointNet2021.11 | 73.3 | — |