Few Shot 3D Point Cloud Classification On 2

评估指标

Overall Accuracy

Standard Deviation

评测结果

各个模型在此基准测试上的表现结果

模型名称	Overall Accuracy	Standard Deviation	Paper Title	Repository
point2vec	98.7	1.2	Point2Vec for Self-Supervised Representation Learning on Point Clouds
Point-JEPA	99.2	0.8	Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud	-
OcCo+PointNet	92.4	1.6	Unsupervised Point Cloud Pre-Training via Occlusion Completion
IDPT	97.9	-	Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Models
PointNet++	42.39	14.2	PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
PCP-MAE	99.1	0.8	PCP-MAE: Learning to Predict Centers for Point Masked Autoencoders
PointCNN	68.64	7.0	PointCNN: Convolution On X-Transformed Points
Point-RAE	98.7	1.3	Regress Before Construct: Regress Autoencoder for Point Cloud Self-supervised Learning
ACT	98.0	1.4	Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?
GPr-Net + Hyp (1024)	82.0	0.9	GPr-Net: Geometric Prototypical Network for Point Cloud Few-Shot Learning
GPr-Net + Hyp (512)	82.7	1.3	GPr-Net: Geometric Prototypical Network for Point Cloud Few-Shot Learning
PointNet	57.81	15.5	PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
Point-LGMask	98.1	1.4	Point-LGMask: Local and Global Contexts Embedding for Point Cloud Pre-training with Multi-Ratio Masking
Point-MAE	97.8	1.8	Masked Autoencoders for Point Cloud Self-supervised Learning
OcCo+DGCNN	92.5	1.9	Unsupervised Point Cloud Pre-Training via Occlusion Completion
3D-JEPA	98.8	0.4	3D-JEPA: A Joint Embedding Predictive Architecture for 3D Self-Supervised Representation Learning	-
MaskPoint	97.2	1.7	Masked Discrimination for Self-Supervised Learning on Point Clouds
SSFSL+PointNet	68.90	9.4	Self-Supervised Few-Shot Learning on Point Clouds
DGCNN	40.8	14.6	Dynamic Graph CNN for Learning on Point Clouds
GPr-Net + Euc (1024)	75.1	2.1	GPr-Net: Geometric Prototypical Network for Point Cloud Few-Shot Learning

0 of 30 row(s) selected.