List your company
ResearchFormerly WizWand

Object Classification on ScanObjectNN OBJ_BG variant

95.18Overall AccuracyReCon
72.424878.332484.2490.1476May 5, 2026May 15, 2026May 26, 2026Jun 5, 2026Jun 16, 2026Jun 26, 2026Jul 7, 2026
Updated 3mo ago

Evaluation results

MethodLinks
ReConBackbone=Attn., Number of trainable parameters (#TP)=43.6 (100%), FLOPs (G)=5.3, Evaluation Protocol=Parameter-Efficient Fine-tuning, Data Modality (Cross-modal vs Single-modal)=cross-modal, Augmentation Strategy=Simple rotational augmentation2026.0595.18
PointMamba + MantisBackbone=SSM, Number of trainable parameters (#TP)=0.6 (4.9%), FLOPs (G)=4.0, Evaluation Protocol=Parameter-Efficient Fine-tuning, Data Modality (Cross-modal vs Single-modal)=single-modal, Augmentation Strategy=Simple rotational augmentation2026.0594.65
ReCon + GAPromptBackbone=Attn., Number of trainable parameters (#TP)=0.6 (1.4%), FLOPs (G)=5.0, Evaluation Protocol=Parameter-Efficient Fine-tuning, Data Modality (Cross-modal vs Single-modal)=cross-modal, Augmentation Strategy=Simple rotational augmentation2026.0594.49
ReCon + DAPTBackbone=Attn., Number of trainable parameters (#TP)=1.1 (2.5%), FLOPs (G)=5.0, Evaluation Protocol=Parameter-Efficient Fine-tuning, Data Modality (Cross-modal vs Single-modal)=cross-modal, Augmentation Strategy=Simple rotational augmentation2026.0594.32
PointMambaBackbone=SSM, Number of trainable parameters (#TP)=12.3 (100%), FLOPs (G)=3.1, Evaluation Protocol=Parameter-Efficient Fine-tuning, Data Modality (Cross-modal vs Single-modal)=single-modal, Augmentation Strategy=Simple rotational augmentation2026.0594.32
I2P-MAEBackbone=Attn., Number of trainable parameters (#TP)=15.3, Evaluation Protocol=Full Fine-tuning, Data Modality (Cross-modal vs Single-modal)=single-modal, Augmentation Strategy=Simple rotational augmentation2026.0594.15
ZigzagPointMambaBackbone=SSM, Number of trainable parameters (#TP)=12.3 (100%), FLOPs (G)=3.1, Evaluation Protocol=Parameter-Efficient Fine-tuning, Data Modality (Cross-modal vs Single-modal)=single-modal, Augmentation Strategy=None2026.0594.15
ZigzagPointMamba + MantisBackbone=SSM, Number of trainable parameters (#TP)=0.6 (4.9%), FLOPs (G)=4.5, Evaluation Protocol=Parameter-Efficient Fine-tuning, Data Modality (Cross-modal vs Single-modal)=single-modal, Augmentation Strategy=None2026.0594.02
PointMamba + PMABackbone=SSM, Number of trainable parameters (#TP)=1.1 (8.9%), FLOPs (G)=5.2, Evaluation Protocol=Parameter-Efficient Fine-tuning, Data Modality (Cross-modal vs Single-modal)=single-modal, Augmentation Strategy=Simple rotational augmentation2026.0593.53
PointGPT-SBackbone=Attn., Number of trainable parameters (#TP)=29.2, FLOPs (G)=5.7, Evaluation Protocol=Full Fine-tuning, Data Modality (Cross-modal vs Single-modal)=single-modal, Augmentation Strategy=Simple rotational augmentation2026.0593.39
ACTBackbone=Attn., Number of trainable parameters (#TP)=22.1, FLOPs (G)=4.8, Evaluation Protocol=Full Fine-tuning, Data Modality (Cross-modal vs Single-modal)=single-modal, Augmentation Strategy=Simple rotational augmentation2026.0593.29
Mamba3D + MantisBackbone=SSM, Number of trainable parameters (#TP)=0.8 (4.7%), FLOPs (G)=4.0, Evaluation Protocol=Parameter-Efficient Fine-tuning, Data Modality (Cross-modal vs Single-modal)=single-modal, Augmentation Strategy=None2026.0593.29
Mamba3DBackbone=SSM, Number of trainable parameters (#TP)=16.9 (100%), FLOPs (G)=3.9, Evaluation Protocol=Parameter-Efficient Fine-tuning, Data Modality (Cross-modal vs Single-modal)=single-modal, Augmentation Strategy=None2026.0593.12
ZigzagPointMamba + PMABackbone=SSM, Number of trainable parameters (#TP)=1.1 (8.9%), FLOPs (G)=5.7, Evaluation Protocol=Parameter-Efficient Fine-tuning, Data Modality (Cross-modal vs Single-modal)=single-modal, Augmentation Strategy=None2026.0593.1
Mamba3DPre-training Representation=Point Cloud2026.0792.94
SI-MambaBackbone=SSM, Number of trainable parameters (#TP)=12.3, FLOPs (G)=3.6, Evaluation Protocol=Full Fine-tuning, Data Modality (Cross-modal vs Single-modal)=single-modal, Augmentation Strategy=None2026.0592.25
Mamba3D + PMABackbone=SSM, Number of trainable parameters (#TP)=1.3 (7.7%), FLOPs (G)=4.7, Evaluation Protocol=Parameter-Efficient Fine-tuning, Data Modality (Cross-modal vs Single-modal)=single-modal, Augmentation Strategy=None2026.0591.97
Point-M2AEBackbone=Attn., Number of trainable parameters (#TP)=15.3, FLOPs (G)=3.6, Evaluation Protocol=Full Fine-tuning, Data Modality (Cross-modal vs Single-modal)=single-modal, Augmentation Strategy=None2026.0591.22
Point-MAE + IDPTBackbone=Attn., Number of trainable parameters (#TP)=1.7 (7.7%), FLOPs (G)=7.2, Evaluation Protocol=Parameter-Efficient Fine-tuning, Data Modality (Cross-modal vs Single-modal)=single-modal, Augmentation Strategy=None2026.0591.22
Point-M2AEPre-training Representation=Point Cloud2026.0791.22
Joint-MAEBackbone=Attn., Evaluation Protocol=Full Fine-tuning, Data Modality (Cross-modal vs Single-modal)=single-modal, Augmentation Strategy=None2026.0590.94
Point-MAE + PointLoRABackbone=Attn., Number of trainable parameters (#TP)=0.8 (3.6%), Evaluation Protocol=Parameter-Efficient Fine-tuning, Data Modality (Cross-modal vs Single-modal)=single-modal, Augmentation Strategy=None2026.0590.71
Point-MAEBackbone=Attn., Number of trainable parameters (#TP)=22.1 (100%), FLOPs (G)=4.8, Evaluation Protocol=Parameter-Efficient Fine-tuning, Data Modality (Cross-modal vs Single-modal)=single-modal, Augmentation Strategy=None2026.0590.02
Point-MAEPre-training Representation=Point Cloud2026.0790.02
GaussFusionPre-training Representation=3D Gaussian2026.0788.98
Point-BERTBackbone=Attn., Number of trainable parameters (#TP)=22.1, FLOPs (G)=4.8, Evaluation Protocol=Full Fine-tuning, Data Modality (Cross-modal vs Single-modal)=single-modal, Augmentation Strategy=None2026.0587.43
PointCNNBackbone=-, Number of trainable parameters (#TP)=0.6, FLOPs (G)=0.9, Evaluation Protocol=Supervised Learning Only, Data Modality (Cross-modal vs Single-modal)=single-modal, Augmentation Strategy=None2026.0586.1
PointCNNPre-training Representation=Point Cloud2026.0786.1
Transformer + OcCoPre-training Representation=Point Cloud2026.0784.85
Gaussian-MAE†Pre-training Representation=3D Gaussian2026.0784.3
DGCNNBackbone=-, Number of trainable parameters (#TP)=1.8, FLOPs (G)=2.4, Evaluation Protocol=Supervised Learning Only, Data Modality (Cross-modal vs Single-modal)=single-modal, Augmentation Strategy=None2026.0582.8
DGCNNPre-training Representation=Point Cloud2026.0782.8
PointNet++Backbone=-, Number of trainable parameters (#TP)=1.5, FLOPs (G)=1.7, Evaluation Protocol=Supervised Learning Only, Data Modality (Cross-modal vs Single-modal)=single-modal, Augmentation Strategy=None2026.0582.3
PointNet++Pre-training Representation=Point Cloud2026.0782.3
TransformerPre-training Representation=Point Cloud2026.0779.86
SpiderCNNPre-training Representation=Point Cloud2026.0777.1
PointNetBackbone=-, Number of trainable parameters (#TP)=3.5, FLOPs (G)=0.5, Evaluation Protocol=Supervised Learning Only, Data Modality (Cross-modal vs Single-modal)=cross-modal, Augmentation Strategy=None2026.0573.3
PointNetPre-training Representation=Point Cloud2026.0773.3