AI Paper Atlas

Research map / Point clouds / Point cloud classification

Not All Neighbors Matter: Point Distribution-Aware Pruning for 3D Point Cloud

Yejin Lee, Donghyun Lee, JungUk Hong, Jae W. Lee, Hongil Yoon

AAAI 2023 · Point clouds › Point cloud classification · approach: Local feature aggregation networks · 8 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Prune neighborhood voxel groups with lower training-set neighbor probability, then retrainMinkUNet-based sparse 3D convolution models · Four datasets (geomean), FP32inference speedup: 1.60×Improved
Use the lossy pruning configuration, allowing up to 1% lower accuracy metric (ablation)MinkUNet-based sparse 3D convolution models · Four datasets (geomean), FP32inference speedup: 1.97×Improved
Prune neighborhood voxel groups with lower training-set neighbor probability, then retrainMinkUNet-based sparse 3D convolution models · Four datasets (geomean), FP32energy efficiency improvement: 1.74×Improved
Use the lossy pruning configuration, allowing up to 1% lower accuracy metric (ablation)MinkUNet-based sparse 3D convolution models · Four datasets (geomean), FP32energy efficiency improvement: 2.22×Improved
Prune neighborhood voxel groups with lower training-set neighbor probabilityMinkUNet-based sparse 3D convolution models · Four datasets (geomean), FP32FLOPs: 49.45%Improved
Allow the lossy pruning configuration (ablation)MinkUNet-based sparse 3D convolution models · Four datasets (geomean), FP32FLOPs: 62.93%Improved
Replace residual blocks with Asymmetrical Residual Blocks (ablation)MinkUNet · Four datasets, FP32inference speedupMixed
Replace residual blocks with Asymmetrical Residual Blocks (ablation)MinkUNet · Four datasetsaccuracyHurt
Apply neighborhood pruning to FP16 models (ablation)MinkUNet-based sparse 3D convolution models · Four datasets (geomean), FP16inference latency improvement: 1.39×Improved
Apply the lossy pruning configuration to FP16 models (ablation)MinkUNet-based sparse 3D convolution models · Four datasets (geomean), FP16inference latency improvement: 1.61×Improved
Apply neighborhood pruning to FP16 models (ablation)MinkUNet-based sparse 3D convolution models · Four datasets (geomean), FP16energy efficiency improvement: 1.30×Improved
Apply the lossy pruning configuration to FP16 models (ablation)MinkUNet-based sparse 3D convolution models · Four datasets (geomean), FP16energy efficiency improvement: 1.47×Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy