List your company
ResearchFormerly WizWand

Few-shot Classification on ModelNet40 10-way 20-shot

96.5AccuracyCSCon
85.99688.72391.4594.177Apr 14, 2023Oct 17, 2023Apr 20, 2024Oct 23, 2024Apr 27, 2025Oct 30, 2025May 5, 2026
Updated 6mo ago

Evaluation results

MethodLinks
CSConProtocol=FULL, Training Paradigm=Self-Supervised Representation Learning, Input Modality=single-modal information2025.1296.5
ReConParadigm=Pre-S-R2026.0396.5
PointMamba + MantisEvaluation Protocol=Parameter-Efficient Fine-Tuning2026.0596.4
Point-PQAEProtocol=FULL, Training Paradigm=Self-Supervised Representation Learning, Input Modality=single-modal information2025.1296.3
PointGPT-SEvaluation Protocol=Full Fine-tuning2026.0596.1
PCP-MAEProtocol=FULL, Training Paradigm=Self-Supervised Representation Learning, Input Modality=single-modal information2025.1295.9
ReConParadigm=Pre-R2026.0395.9
Point-RAEvoting=false2023.0995.8
RECON (Full-FT)Publication=ICML'23, Fine-tuning Protocol=Full Fine-Tuning2025.0495.8
RECON+ PointLoRAPublication=Ours, Fine-tuning Protocol=Efficient Fine-Tuning2025.0495.8
Point-FEMAEProtocol=FULL, Training Paradigm=Self-Supervised Representation Learning, Input Modality=single-modal information2025.1295.8
PointLAMAProtocol=FULL, Training Paradigm=Self-Supervised Representation Learning, Input Modality=single-modal information2025.1295.8
TAPProtocol=FULL, Training Paradigm=Self-Supervised Representation Learning, Input Modality=cross-modal information and teacher models2025.1295.8
ReConProtocol=FULL, Training Paradigm=Self-Supervised Representation Learning, Input Modality=cross-modal information and teacher models2025.1295.8
CSConEvaluation Protocol=MLP-32025.1295.8
ReConEvaluation Protocol=MLP-32025.1295.7
PCP-MAEEvaluation Protocol=MLP-32025.1295.7
HyperPointParadigm=Pre-S-R2026.0395.7
ACTLearning Protocol=Full Fine-tuning2023.0495.6
ACTvoting=false2023.0995.6
ACTPublication=ICLR'23, Fine-tuning Protocol=Full Fine-Tuning2025.0495.6
RECON+ PPTPublication=arXiv'24, Fine-tuning Protocol=Efficient Fine-Tuning2025.0495.6
ACTProtocol=FULL, Training Paradigm=Self-Supervised Representation Learning, Input Modality=cross-modal information and teacher models2025.1295.6
Point-MAEParadigm=Pre-S-R2026.0395.6
HyperPointParadigm=Pre-S2026.0395.6
ACTEvaluation Protocol=Full Fine-tuning2026.0595.6
PointMambaEvaluation Protocol=Parameter-Efficient Fine-Tuning2026.0595.6
ACT w/ IDPTLearning Protocol=IDPT2023.0495.5
I2P-MAEvoting=false2023.0995.5
RECON+ IDPTPublication=ICCV'23, Fine-tuning Protocol=Efficient Fine-Tuning2025.0495.5
I2P-MAEProtocol=FULL, Training Paradigm=Self-Supervised Representation Learning, Input Modality=cross-modal information and teacher models2025.1295.5
Point-FEMAEEvaluation Protocol=MLP-LINEAR2025.1295.5
CSConEvaluation Protocol=MLP-LINEAR2025.1295.5
Point-FEMAEEvaluation Protocol=MLP-32025.1295.5
HyperPointParadigm=Pre-R2026.0395.5
ZigzagPointMamba + MantisEvaluation Protocol=Parameter-Efficient Fine-Tuning2026.0595.5
Point-MAE w/ IDPTLearning Protocol=IDPT2023.0495.4
ReConEvaluation Protocol=MLP-LINEAR2025.1295.4
Point-CMAEProtocol=FULL, Training Paradigm=Self-Supervised Representation Learning, Input Modality=single-modal information2025.1295.3
Mamba3D + MantisEvaluation Protocol=Parameter-Efficient Fine-Tuning2026.0595.3
MAMBA3D+P-MLearning Mode=Self-supervised Pre-training, Pre-training Strategy=Point-MAE, Voting=false2024.0495.2
PointGPTProtocol=FULL, Training Paradigm=Self-Supervised Representation Learning, Input Modality=single-modal information2025.1295.2
DAP-MAEProtocol=FULL, Training Paradigm=Self-Supervised Representation Learning, Input Modality=single-modal information2025.1295.2
Mamba3DEvaluation Protocol=Parameter-Efficient Fine-Tuning2026.0595.2
Joint-MAEProtocol=FULL, Training Paradigm=Self-Supervised Representation Learning, Input Modality=cross-modal information and teacher models2025.1295.1
Point-MAELearning Protocol=Full Fine-tuning2023.0495
Point-M2AELearning Protocol=Full Fine-tuning2023.0495
Point-MAEvoting=false2023.0995
Point-M2AEvoting=false2023.0995
Point-MAELearning Mode=Self-supervised Pre-training, Voting=false2024.0495
Point-MAEPublication=ECCV'22, Fine-tuning Protocol=Full Fine-Tuning2025.0495
Point-M2AEPublication=NeurIPS'22, Fine-tuning Protocol=Full Fine-Tuning2025.0495
Point-MAEProtocol=FULL, Training Paradigm=Self-Supervised Representation Learning, Input Modality=single-modal information2025.1295
Point-M2AEProtocol=FULL, Training Paradigm=Self-Supervised Representation Learning, Input Modality=single-modal information2025.1295
Point-MAEParadigm=Pre-S2026.0395
Point-MAEParadigm=Pre-R2026.0395
Point-MAEEvaluation Protocol=Full Fine-tuning2026.0595
ReConParadigm=Pre-S2026.0394.9
ACTEvaluation Protocol=MLP-32025.1294.7
Point-PQAEEvaluation Protocol=MLP-32025.1294.7
RECON+ DAPTPublication=CVPR'24, Fine-tuning Protocol=Efficient Fine-Tuning2025.0494.6
MAMBA3D+P-BLearning Mode=Self-supervised Pre-training, Pre-training Strategy=Point-BERT, Voting=false2024.0494.5
Point-CMAEEvaluation Protocol=MLP-32025.1294.4
ZigzagPointMambaEvaluation Protocol=Parameter-Efficient Fine-Tuning2026.0594.2
SLNet-MMethod Category=Parametric2026.0394
PCP-MAEEvaluation Protocol=MLP-LINEAR2025.1293.9
Point-MAEEvaluation Protocol=MLP-32025.1293.8
Point-BERT w/ IDPTLearning Protocol=IDPT2023.0493.6
EPCLLearning Protocol=Full Fine-tuning2023.0493.5
Point-PQAEEvaluation Protocol=MLP-LINEAR2025.1293.5
SLNet-SMethod Category=Parametric2026.0393.5
MaskPointLearning Protocol=Full Fine-tuning2023.0493.4
MaskPointvoting=false2023.0993.4
MaskPointLearning Mode=Self-supervised Pre-training, Voting=false2024.0493.4
MaskPointPublication=ECCV'22, Fine-tuning Protocol=Full Fine-Tuning2025.0493.4
MaskPointProtocol=FULL, Training Paradigm=Self-Supervised Representation Learning, Input Modality=single-modal information2025.1293.4
MaskPointEvaluation Protocol=Full Fine-tuning2026.0593.4
ReConEvaluation Protocol=Full Fine-tuning2026.0593.3
MAMBA3DLearning Mode=Supervised Learning, Voting=false2024.0493.1
PointMambaLearning Mode=Self-supervised Pre-training, Voting=false2024.0492.8
Point-BERTLearning Protocol=Full Fine-tuning2023.0492.7
Point-BERTvoting=false2023.0992.7
Point-BERTLearning Mode=Self-supervised Pre-training, Voting=false2024.0492.7
Point-BERTPublication=CVPR'22, Fine-tuning Protocol=Full Fine-Tuning2025.0492.7
Point-BERTProtocol=FULL, Training Paradigm=Self-Supervised Representation Learning, Input Modality=single-modal information2025.1292.7
Point-BERTEvaluation Protocol=Full Fine-tuning2026.0592.7
Transformer-OcCoLearning Protocol=Full Fine-tuning2023.0492.4
OcCoLearning Mode=Self-supervised Pre-training, Voting=false2024.0492.4
OcCoPublication=ICCV'21, Fine-tuning Protocol=Full Fine-Tuning2025.0492.4
Point-CMAEEvaluation Protocol=MLP-LINEAR2025.1292.3
ACTEvaluation Protocol=MLP-LINEAR2025.1290.7
Point-MAEEvaluation Protocol=MLP-LINEAR2025.1289.7
Transformervoting=false2023.0989.4
TransformerLearning Mode=Supervised Learning, Voting=false2024.0489.4
NPNetMethod Category=Non-Parametric2026.0387.6
DGCNN-OcCoLearning Protocol=Full Fine-tuning2023.0486.5
DGCNN+OcCovoting=false2023.0986.5
DGCNN+OcCoLearning Mode=Self-supervised Pre-training, Pre-training Strategy=OcCo, Voting=false2024.0486.5
OcCoProtocol=FULL, Training Paradigm=Supervised Learning Only2025.1286.5
Point-GNMethod Category=Non-Parametric2026.0386.4