List your company
ResearchFormerly WizWand

Few-shot Classification on ModelNet40 5-way 10-shot

98AccuracyPointGPT-S
28.94446.87264.882.728Apr 14, 2023Oct 17, 2023Apr 20, 2024Oct 23, 2024Apr 27, 2025Oct 30, 2025May 5, 2026
Updated 6mo ago

Evaluation results

MethodLinks
PointGPT-SEvaluation Protocol=Full Fine-tuning2026.0598
DAP-MAEProtocol=FULL, Training Paradigm=Self-Supervised Representation Learning, Input Modality=single-modal information2025.1297.5
CSConProtocol=FULL, Training Paradigm=Self-Supervised Representation Learning, Input Modality=single-modal information2025.1297.5
PCP-MAEProtocol=FULL, Training Paradigm=Self-Supervised Representation Learning, Input Modality=single-modal information2025.1297.4
ReConEvaluation Protocol=MLP-32025.1297.4
CSConEvaluation Protocol=MLP-32025.1297.4
Point-MAE w/ IDPTLearning Protocol=IDPT2023.0497.3
Point-RAEvoting=false2023.0997.3
RECON (Full-FT)Publication=ICML'23, Fine-tuning Protocol=Full Fine-Tuning2025.0497.3
TAPProtocol=FULL, Training Paradigm=Self-Supervised Representation Learning, Input Modality=cross-modal information and teacher models2025.1297.3
ReConProtocol=FULL, Training Paradigm=Self-Supervised Representation Learning, Input Modality=cross-modal information and teacher models2025.1297.3
ReConEvaluation Protocol=Full Fine-tuning2026.0597.3
Point-FEMAEProtocol=FULL, Training Paradigm=Self-Supervised Representation Learning, Input Modality=single-modal information2025.1297.2
PointLAMAProtocol=FULL, Training Paradigm=Self-Supervised Representation Learning, Input Modality=single-modal information2025.1297.2
PointMamba + MantisEvaluation Protocol=Parameter-Efficient Fine-Tuning2026.0597.2
I2P-MAEvoting=false2023.0997
RECON+ PPTPublication=arXiv'24, Fine-tuning Protocol=Efficient Fine-Tuning2025.0497
I2P-MAEProtocol=FULL, Training Paradigm=Self-Supervised Representation Learning, Input Modality=cross-modal information and teacher models2025.1297
RECON+ IDPTPublication=ICCV'23, Fine-tuning Protocol=Efficient Fine-Tuning2025.0496.9
RECON+ PointLoRAPublication=Ours, Fine-tuning Protocol=Efficient Fine-Tuning2025.0496.9
Point-PQAEProtocol=FULL, Training Paradigm=Self-Supervised Representation Learning, Input Modality=single-modal information2025.1296.9
ReConEvaluation Protocol=MLP-LINEAR2025.1296.9
CSConEvaluation Protocol=MLP-LINEAR2025.1296.9
PointMambaEvaluation Protocol=Parameter-Efficient Fine-Tuning2026.0596.9
Point-M2AELearning Protocol=Full Fine-tuning2023.0496.8
ACTLearning Protocol=Full Fine-tuning2023.0496.8
Point-M2AEvoting=false2023.0996.8
ACTvoting=false2023.0996.8
Point-M2AEPublication=NeurIPS'22, Fine-tuning Protocol=Full Fine-Tuning2025.0496.8
ACTPublication=ICLR'23, Fine-tuning Protocol=Full Fine-Tuning2025.0496.8
Point-M2AEProtocol=FULL, Training Paradigm=Self-Supervised Representation Learning, Input Modality=single-modal information2025.1296.8
PointGPTProtocol=FULL, Training Paradigm=Self-Supervised Representation Learning, Input Modality=single-modal information2025.1296.8
ACTProtocol=FULL, Training Paradigm=Self-Supervised Representation Learning, Input Modality=cross-modal information and teacher models2025.1296.8
ACTEvaluation Protocol=Full Fine-tuning2026.0596.8
ACT w/ IDPTLearning Protocol=IDPT2023.0496.7
Point-CMAEProtocol=FULL, Training Paradigm=Self-Supervised Representation Learning, Input Modality=single-modal information2025.1296.7
Joint-MAEProtocol=FULL, Training Paradigm=Self-Supervised Representation Learning, Input Modality=cross-modal information and teacher models2025.1296.7
PCP-MAEEvaluation Protocol=MLP-32025.1296.7
MAMBA3D+P-MLearning Mode=Self-supervised Pre-training, Pre-training Strategy=Point-MAE, Voting=false2024.0496.4
Point-FEMAEEvaluation Protocol=MLP-LINEAR2025.1296.4
Point-FEMAEEvaluation Protocol=MLP-32025.1296.4
Mamba3DEvaluation Protocol=Parameter-Efficient Fine-Tuning2026.0596.4
Point-MAELearning Protocol=Full Fine-tuning2023.0496.3
Point-MAEvoting=false2023.0996.3
Point-MAELearning Mode=Self-supervised Pre-training, Voting=false2024.0496.3
Point-MAEPublication=ECCV'22, Fine-tuning Protocol=Full Fine-Tuning2025.0496.3
Point-MAEProtocol=FULL, Training Paradigm=Self-Supervised Representation Learning, Input Modality=single-modal information2025.1296.3
Point-MAEEvaluation Protocol=Full Fine-tuning2026.0596.3
ZigzagPointMamba + MantisEvaluation Protocol=Parameter-Efficient Fine-Tuning2026.0596.2
Point-BERT w/ IDPTLearning Protocol=IDPT2023.0496
ZigzagPointMambaEvaluation Protocol=Parameter-Efficient Fine-Tuning2026.0596
ACTEvaluation Protocol=MLP-32025.1295.9
Point-CMAEEvaluation Protocol=MLP-32025.1295.9
MAMBA3D+P-BLearning Mode=Self-supervised Pre-training, Pre-training Strategy=Point-BERT, Voting=false2024.0495.8
RECON+ DAPTPublication=CVPR'24, Fine-tuning Protocol=Efficient Fine-Tuning2025.0495.6
Point-PQAEEvaluation Protocol=MLP-32025.1295.3
Mamba3D + MantisEvaluation Protocol=Parameter-Efficient Fine-Tuning2026.0595.3
EPCLLearning Protocol=Full Fine-tuning2023.0495.1
MaskPointLearning Protocol=Full Fine-tuning2023.0495
MaskPointvoting=false2023.0995
PointMambaLearning Mode=Self-supervised Pre-training, Voting=false2024.0495
MaskPointLearning Mode=Self-supervised Pre-training, Voting=false2024.0495
MaskPointPublication=ECCV'22, Fine-tuning Protocol=Full Fine-Tuning2025.0495
MaskPointProtocol=FULL, Training Paradigm=Self-Supervised Representation Learning, Input Modality=single-modal information2025.1295
Point-MAEEvaluation Protocol=MLP-32025.1295
MaskPointEvaluation Protocol=Full Fine-tuning2026.0595
Point-BERTLearning Protocol=Full Fine-tuning2023.0494.6
Point-BERTvoting=false2023.0994.6
Point-BERTLearning Mode=Self-supervised Pre-training, Voting=false2024.0494.6
Point-BERTPublication=CVPR'22, Fine-tuning Protocol=Full Fine-Tuning2025.0494.6
Point-BERTProtocol=FULL, Training Paradigm=Self-Supervised Representation Learning, Input Modality=single-modal information2025.1294.6
Point-BERTEvaluation Protocol=Full Fine-tuning2026.0594.6
Transformer-OcCoLearning Protocol=Full Fine-tuning2023.0494
OcCoLearning Mode=Self-supervised Pre-training, Voting=false2024.0494
OcCoPublication=ICCV'21, Fine-tuning Protocol=Full Fine-Tuning2025.0494
PCP-MAEEvaluation Protocol=MLP-LINEAR2025.1294
Point-PQAEEvaluation Protocol=MLP-LINEAR2025.1293
MAMBA3DLearning Mode=Supervised Learning, Voting=false2024.0492.6
NPNetMethod Category=Non-Parametric2026.0392
ACTEvaluation Protocol=MLP-LINEAR2025.1291.8
Point-MAEEvaluation Protocol=MLP-LINEAR2025.1291.1
Point-GNMethod Category=Non-Parametric2026.0390.7
DGCNN-OcCoLearning Protocol=Full Fine-tuning2023.0490.6
DGCNN+OcCovoting=false2023.0990.6
DGCNN+OcCoLearning Mode=Self-supervised Pre-training, Pre-training Strategy=OcCo, Voting=false2024.0490.6
OcCoProtocol=FULL, Training Paradigm=Supervised Learning Only, Input Modality=single-modal information2025.1290.6
Point-CMAEEvaluation Protocol=MLP-LINEAR2025.1290.4
SLNet-MMethod Category=Parametric2026.0389
Point-NNMethod Category=Non-Parametric2026.0388.8
Transformervoting=false2023.0987.8
TransformerLearning Mode=Supervised Learning, Voting=false2024.0487.8
SLNet-SMethod Category=Parametric2026.0384
PointCNNMethod Category=Parametric2026.0365.4
3D-GANMethod Category=Parametric2026.0355.8
PointNetProtocol=FULL, Training Paradigm=Supervised Learning Only, Input Modality=single-modal information2025.1252
PointNetMethod Category=Parametric2026.0352
PointNet++Method Category=Parametric2026.0338.5
FoldingNetMethod Category=Parametric2026.0333.4
DGCNNvoting=false2023.0931.6
DGCNNLearning Mode=Supervised Learning, Voting=false2024.0431.6