AI Paper Atlas

Research map / Point clouds / Point cloud classification

PointAugment: An Auto-Augmentation Framework for Point Cloud Classification

Ruihui Li, Xianzhi Li, Pheng-Ann Heng, Chi-Wing Fu

CVPR 2020 · Point clouds › Point cloud classification · approach: Local feature aggregation networks · 191 citations (OpenAlex)

This paper tried a common change: Add dropout

Add dropout to displacement and transformation · ModelNet40 · accuracy: 92.5 -> 92.8 Improved

What 795 accepted papers report for this change

See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.

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
Replace conventional data augmentation with PointAugmentFour classifiers · ModelNet40accuracy: 89.2 -> 90.9; 90.7 -> 92.9; 91.7 -> 92.7; 92.2 -> 93.4Improved
Replace conventional data augmentation with PointAugmentFour classifiers · ModelNet10accuracy: 91.9 -> 94.1; 93.3 -> 95.8; 94.2 -> 96.0; 94.8 -> 96.7Improved
Replace conventional data augmentation with PointAugmentFour classifiers · SHREC16accuracy: 84.4 -> 88.4; 85.1 -> 89.5; 86.6 -> 90.1; 87.0 -> 90.6Improved
Replace conventional data augmentation with PointAugmentFour classifiers · ModelNet40mAP: 70.5 -> 75.8; 81.3 -> 86.7; 83.2 -> 86.6; 85.3 -> 89.0Improved
Train with PointAugment rather than conventional DAPointNet++ · ModelNet40 test corruption: jitteringaccuracy: 90.3 -> 92.8Improved
Train with PointAugment rather than conventional DAPointNet++ · ModelNet40 test corruption: scaling 0.9accuracy: 90.3 -> 92.8Improved
Train with PointAugment rather than conventional DAPointNet++ · ModelNet40 test corruption: scaling 1.1accuracy: 90.3 -> 92.8Improved
Train with PointAugment rather than conventional DAPointNet++ · ModelNet40 test corruption: rotation 90°accuracy: 89.9 -> 92.7Improved
Train with PointAugment rather than conventional DAPointNet++ · ModelNet40 test corruption: rotation 180°accuracy: 89.7 -> 92.6Improved
Add point-wise displacement (ablation)PointNet++ with conventional DA · ModelNet40accuracy: 90.7 -> 91.7Improved
Add shape-wise transformation (ablation)PointNet++ with conventional DA · ModelNet40accuracy: 90.7 -> 91.9Improved
Add shape-wise transformation to point-wise displacement (ablation)PointNet++ augmentor · ModelNet40accuracy: 91.7 -> 92.5Improved

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