HyperAIHyperAI超神経

Command Palette

Search for a command to run...

プラットフォーム

3D Point Cloud Classification On Scanobjectnn

評価指標

Mean Accuracy
OBJ-BG (OA)
OBJ-ONLY (OA)
Overall Accuracy

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

Paper Title
OmniVec2---97.2OmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning
PointGST-99.4897.7696.18Parameter-Efficient Fine-Tuning in Spectral Domain for Point Cloud Learning
OmniVec---96.1OmniVec: Learning robust representations with cross modal sharing
GPSFormer93.8--95.4GPSFormer: A Global Perception and Local Structure Fitting-based Transformer for Point Cloud Understanding
ReCon++-98.8097.5995.25ShapeLLM: Universal 3D Object Understanding for Embodied Interaction
PointGPT-97.296.693.4PointGPT: Auto-regressively Generative Pre-training from Point Clouds
GPSFormer-elite92.51--93.30GPSFormer: A Global Perception and Local Structure Fitting-based Transformer for Point Cloud Understanding
Mamba3D-94.4992.4392.64Mamba3D: Enhancing Local Features for 3D Point Cloud Analysis via State Space Model
Mamba3D (no voting)-92.9492.0891.81Mamba3D: Enhancing Local Features for 3D Point Cloud Analysis via State Space Model
ULIP-2 + PointNeXt91.2--91.5ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understanding
ReCon-95.3593.8091.26Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining
ULIP-2 + PointNeXt (no voting)90.3--90.8ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understanding
ReCon (no voting)-95.1893.2990.63Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining
DeLA89.3--90.4Decoupled Local Aggregation for Point Cloud Learning
PCP-MAE-95.5294.3290.35PCP-MAE: Learning to Predict Centers for Point Masked Autoencoders
PointConT88.5--90.3Point Cloud Classification Using Content-based Transformer via Clustering in Feature Space
Point-RAE (no voting)-95.5393.6390.28Regress Before Construct: Regress Autoencoder for Point Cloud Self-supervised Learning
Point-FEMAE-95.1893.2990.22Towards Compact 3D Representations via Point Feature Enhancement Masked Autoencoders
I2P-MAE (no voting)-94.1591.5790.11Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoders
ULIP + PointNeXt88.6--89.7ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding
0 of 75 row(s) selected.