HyperAI超神経

Few Shot 3D Point Cloud Classification On 4

評価指標

Overall Accuracy
Standard Deviation

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

モデル名
Overall Accuracy
Standard Deviation
Paper TitleRepository
Point-LGMask95.13.4Point-LGMask: Local and Global Contexts Embedding for Point Cloud Pre-training with Multi-Ratio Masking
SSFSL+PointNet50.105.0Self-Supervised Few-Shot Learning on Point Clouds
ACT95.62.8Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?
PointGPT96.12.8PointGPT: Auto-regressively Generative Pre-training from Point Clouds
Point-MAE95.03.0Masked Autoencoders for Point Cloud Self-supervised Learning
GPr-Net + Hyp (512)73.82.0GPr-Net: Geometric Prototypical Network for Point Cloud Few-Shot Learning
CrossMoCo91.03.4CrossMoCo: Multi-modal Momentum Contrastive Learning for Point Cloud
GPr-Net + Euc (512)63.32.2GPr-Net: Geometric Prototypical Network for Point Cloud Few-Shot Learning
PCP-MAE95.92.7PCP-MAE: Learning to Predict Centers for Point Masked Autoencoders
OTMae3D95.62.6--
ReCon++96.53.0ShapeLLM: Universal 3D Object Understanding for Embodied Interaction
PointNet35.2013.5PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
PointNet++18.807.0PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
PointCNN49.957.2PointCNN: Convolution On X-Transformed Points
GPr-Net + Euc (1024)63.42.0GPr-Net: Geometric Prototypical Network for Point Cloud Few-Shot Learning
DGCNN16.91.5Dynamic Graph CNN for Learning on Point Clouds
Point-RAE95.83.0Regress Before Construct: Regress Autoencoder for Point Cloud Self-supervised Learning
OcCo+PointNet89.71.5Unsupervised Point Cloud Pre-Training via Occlusion Completion
Point-M2AE95.03.0Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training
IDPT95.4-Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Models
0 of 31 row(s) selected.