List your company
ResearchFormerly WizWand

Object Classification on ScanObjectNN OBJ_ONLY variant

93.63Overall AccuracyReCon
78.622882.518986.41590.3111May 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 augmentation2026.0593.63
ZigzagPointMamba + MantisBackbone=SSM, Number of trainable parameters (#TP)=0.6 (4.9%), FLOPs (G)=4.5, Evaluation Protocol=Parameter-Efficient Fine-tuning2026.0593.27
PointMamba + MantisBackbone=SSM, Number of trainable parameters (#TP)=0.6 (4.9%), FLOPs (G)=4.0, Evaluation Protocol=Parameter-Efficient Fine-tuning, Augmentation Strategy=Simple rotational augmentation2026.0593.14
Mamba3D + MantisBackbone=SSM, Number of trainable parameters (#TP)=0.8 (4.7%), FLOPs (G)=4.0, Evaluation Protocol=Parameter-Efficient Fine-tuning2026.0592.77
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 augmentation2026.0592.6
PointMambaBackbone=SSM, Number of trainable parameters (#TP)=12.3 (100%), FLOPs (G)=3.1, Evaluation Protocol=Parameter-Efficient Fine-tuning, Augmentation Strategy=Simple rotational augmentation2026.0592.6
PointGPT-SBackbone=Attn., Number of trainable parameters (#TP)=29.2, FLOPs (G)=5.7, Evaluation Protocol=Full Fine-tuning, Augmentation Strategy=Simple rotational augmentation2026.0592.43
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 augmentation2026.0592.43
ZigzagPointMambaBackbone=SSM, Number of trainable parameters (#TP)=12.3 (100%), FLOPs (G)=3.1, Evaluation Protocol=Parameter-Efficient Fine-tuning2026.0592.1
Mamba3DBackbone=SSM, Number of trainable parameters (#TP)=16.9 (100%), FLOPs (G)=3.9, Evaluation Protocol=Parameter-Efficient Fine-tuning2026.0592.08
Mamba3DPre-training Representation=Point Cloud2026.0792.08
ACTBackbone=Attn., Number of trainable parameters (#TP)=22.1, FLOPs (G)=4.8, Evaluation Protocol=Full Fine-tuning, Augmentation Strategy=Simple rotational augmentation2026.0591.91
I2P-MAEBackbone=Attn., Number of trainable parameters (#TP)=15.3, Evaluation Protocol=Full Fine-tuning, Augmentation Strategy=Simple rotational augmentation2026.0591.57
SI-MambaBackbone=SSM, Number of trainable parameters (#TP)=12.3, FLOPs (G)=3.6, Evaluation Protocol=Full Fine-tuning2026.0591.39
PointMamba + PMABackbone=SSM, Number of trainable parameters (#TP)=1.1 (8.9%), FLOPs (G)=5.2, Evaluation Protocol=Parameter-Efficient Fine-tuning, Augmentation Strategy=Simple rotational augmentation2026.0591.32
Point-MAE + IDPTBackbone=Attn., Number of trainable parameters (#TP)=1.7 (7.7%), FLOPs (G)=7.2, Evaluation Protocol=Parameter-Efficient Fine-tuning2026.0590.02
Mamba3D + PMABackbone=SSM, Number of trainable parameters (#TP)=1.3 (7.7%), FLOPs (G)=4.7, Evaluation Protocol=Parameter-Efficient Fine-tuning2026.0589.64
ZigzagPointMamba + PMABackbone=SSM, Number of trainable parameters (#TP)=1.1 (8.9%), FLOPs (G)=5.7, Evaluation Protocol=Parameter-Efficient Fine-tuning2026.0589.53
Point-MAE + PointLoRABackbone=Attn., Number of trainable parameters (#TP)=0.8 (3.6%), Evaluation Protocol=Parameter-Efficient Fine-tuning2026.0589.33
Joint-MAEBackbone=Attn., Evaluation Protocol=Full Fine-tuning2026.0588.86
Point-M2AEBackbone=Attn., Number of trainable parameters (#TP)=15.3, FLOPs (G)=3.6, Evaluation Protocol=Full Fine-tuning2026.0588.81
Point-M2AEPre-training Representation=Point Cloud2026.0788.81
GaussFusionPre-training Representation=3D Gaussian2026.0788.47
Point-MAEBackbone=Attn., Number of trainable parameters (#TP)=22.1 (100%), FLOPs (G)=4.8, Evaluation Protocol=Parameter-Efficient Fine-tuning2026.0588.29
Point-MAEPre-training Representation=Point Cloud2026.0788.29
Point-BERTBackbone=Attn., Number of trainable parameters (#TP)=22.1, FLOPs (G)=4.8, Evaluation Protocol=Full Fine-tuning2026.0588.12
Gaussian-MAE†Pre-training Representation=3D Gaussian2026.0786.23
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-modal2026.0586.2
DGCNNPre-training Representation=Point Cloud2026.0786.2
Transformer + OcCoPre-training Representation=Point Cloud2026.0785.54
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-modal2026.0585.5
PointCNNPre-training Representation=Point Cloud2026.0785.5
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-modal2026.0584.3
PointNet++Pre-training Representation=Point Cloud2026.0784.3
TransformerPre-training Representation=Point Cloud2026.0780.55
SpiderCNNPre-training Representation=Point Cloud2026.0779.5
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-modal2026.0579.2
PointNetPre-training Representation=Point Cloud2026.0779.2