3D object recognition on ScanObjectNN OBJ_BG (test)
94.49Top-1 AccuracyPointGST
Evaluation Results
| Method | Links | |
|---|---|---|
| PointGSTPre-trained model=RECON [62], Fine-tuning strategy=PointGST [56], #Param. (M)=0.6 (2.77%), #GFLOPs=4.81(↑)2025.12 | 94.49 | |
| FullPre-trained model=RECON [62], Fine-tuning strategy=Full, #Param. (M)=22.1 (100%), #GFLOPs=4.762025.12 | 94.32 | |
| DAPTPre-trained model=RECON [62], Fine-tuning strategy=DAPT [41], #Param. (M)=1.1 (4.97%), #GFLOPs=4.96(↑)2025.12 | 94.32 | |
| CLoRAPre-trained model=RECON [62], Fine-tuning strategy=CLoRA(ours), #Param. (M)=0.4 (1.81%), #GFLOPs=4.76(-)2025.12 | 94.32 | |
| PointLoRAPre-trained model=RECON [62], Fine-tuning strategy=PointLoRA [64], #Param. (M)=0.8 (3.43%), #GFLOPs=5.06(↑)2025.12 | 93.46 | |
| IDPTPre-trained model=RECON [62], Fine-tuning strategy=IDPT [55], #Param. (M)=1.7 (7.69%), #GFLOPs=7.10(↑)2025.12 | 93.29 | |
| Point-PEFTPre-trained model=RECON [62], Fine-tuning strategy=Point-PEFT [63], #Param. (M)=0.7 (3.13%), #GFLOPs=7.61(↑)2025.12 | 91.91 | |
| PointGSTPre-trained model=Point-MAE [61], Fine-tuning strategy=PointGST [56], #Param. (M)=0.6 (2.77%), #GFLOPs=4.81(↑)2025.12 | 91.74 | |
| CLoRAPre-trained model=Point-BERT [60], Fine-tuning strategy=CLoRA(ours), #Param. (M)=0.3 (1.36%), #GFLOPs=4.76(-)2025.12 | 91.74 | |
| CLoRAPre-trained model=Point-MAE [61], Fine-tuning strategy=CLoRA(ours), #Param. (M)=0.3 (1.36%), #GFLOPs=4.76(-)2025.12 | 91.57 | |
| PointGSTPre-trained model=Point-BERT [60], Fine-tuning strategy=PointGST [56], #Param. (M)=0.6 (2.77%), #GFLOPs=4.81(↑)2025.12 | 91.39 | |
| IDPTPre-trained model=Point-MAE [61], Fine-tuning strategy=IDPT [55], #Param. (M)=1.7 (7.69%), #GFLOPs=7.10(↑)2025.12 | 91.22 | |
| DAPTPre-trained model=Point-BERT [60], Fine-tuning strategy=DAPT [41], #Param. (M)=1.1 (4.97%), #GFLOPs=4.96(↑)2025.12 | 91.05 | |
| DAPTPre-trained model=Point-MAE [61], Fine-tuning strategy=DAPT [41], #Param. (M)=1.1 (4.97%), #GFLOPs=4.96(↑)2025.12 | 90.88 | |
| PointLoRAPre-trained model=Point-MAE [61], Fine-tuning strategy=PointLoRA [64], #Param. (M)=0.8 (3.43%), #GFLOPs=5.06(↑)2025.12 | 90.71 | |
| FullPre-trained model=Point-MAE [61], Fine-tuning strategy=Full, #Param. (M)=22.1 (100%), #GFLOPs=4.762025.12 | 90.02 | |
| PointLoRAPre-trained model=Point-BERT [60], Fine-tuning strategy=PointLoRA [64], #Param. (M)=0.9 (4.07%), #GFLOPs=5.06(↑)2025.12 | 89.85 | |
| Point-PEFTPre-trained model=Point-MAE [61], Fine-tuning strategy=Point-PEFT [63], #Param. (M)=0.7 (3.13%), #GFLOPs=7.61(↑)2025.12 | 89.67 | |
| Point-PEFTPre-trained model=Point-BERT [60], Fine-tuning strategy=Point-PEFT [63], #Param. (M)=0.7 (3.13%), #GFLOPs=7.61(↑)2025.12 | 88.81 | |
| IDPTPre-trained model=Point-BERT [60], Fine-tuning strategy=IDPT [55], #Param. (M)=1.7 (7.69%), #GFLOPs=7.10(↑)2025.12 | 88.12 | |
| FullPre-trained model=Point-BERT [60], Fine-tuning strategy=Full, #Param. (M)=22.1 (100%), #GFLOPs=4.762025.12 | 87.43 | |
| SUGAR (single)Pretrain data=Ensembled (no LVIS), Evaluation protocol=zero-shot, Input Modality=colored point clouds2024.04 | 68 | |
| SUGAR (multi)Pretrain data=Ensembled (no LVIS), Evaluation protocol=zero-shot, Input Modality=colored point clouds2024.04 | 65.6 | |
| SUGAR (single)Pretrain data=Ensembled (no LVIS), Evaluation protocol=zero-shot, Input Modality=uncolored point clouds2024.04 | 56.2 | |
| SUGAR (multi)Pretrain data=Ensembled (no LVIS), Evaluation protocol=zero-shot, Input Modality=uncolored point clouds2024.04 | 53.2 | |
| OpenShape-PointBERTPretrain data=Ensembled (no LVIS), Evaluation protocol=zero-shot, Input Modality=colored point clouds2024.04 | 52.6 | |
| OpenShape-PointBERTPretrain data=Ensembled (no LVIS), Evaluation protocol=zero-shot, Input Modality=uncolored point clouds2024.04 | 51.4 | |
| SUGAR (multi)Pretrain data=ShapeNet, Evaluation protocol=zero-shot, Input Modality=colored point clouds2024.04 | 50.8 | |
| SUGAR (single)Pretrain data=ShapeNet, Evaluation protocol=zero-shot, Input Modality=colored point clouds2024.04 | 50.3 | |
| SUGAR (multi)Pretrain data=ShapeNet, Evaluation protocol=zero-shot, Input Modality=uncolored point clouds2024.04 | 47.9 | |
| SUGAR (single)Pretrain data=ShapeNet, Evaluation protocol=zero-shot, Input Modality=uncolored point clouds2024.04 | 46.3 | |
| OpenShape-PointBERTPretrain data=ShapeNet, Evaluation protocol=zero-shot, Input Modality=colored point clouds2024.04 | 42.4 | |
| OpenShape-PointBERTPretrain data=ShapeNet, Evaluation protocol=zero-shot, Input Modality=uncolored point clouds2024.04 | 41.9 | |
| ReConPretrain data=ShapeNet, Evaluation protocol=zero-shot, Input Modality=uncolored point clouds2024.04 | 38 | |
| CLIP2PointPretrain data=ShapeNet, Evaluation protocol=zero-shot, Input Modality=uncolored point clouds2024.04 | 30.5 |