AI Paper Atlas

Research map / Point clouds / Point cloud classification

Point Cloud Processing via Recurrent Set Encoding

Pengxiang Wu, Chao Chen, Jingru Yi, Dimitris Metaxas

AAAI 2019 · Point clouds › Point cloud classification · approach: Local feature aggregation networks · 13 citations (OpenAlex)

This paper tried a common change: Add dropout

Add random point dropout during training · ModelNet40, 1024 points · accuracy: 90.2 -> 91.1 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.

Read the paper

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 the MLP plus global max-pooling encoder with the recurrent set encoder (ablation)RCNet · ModelNet40accuracy: 89.1 -> 91.6Improved
Ensemble RCNets with beam depths along x, y, and zRCNet · ModelNet40accuracy: 91.6 -> 92.3Improved
Ensemble RCNets with beam depths along x, y, and zRCNet · ShapeNet part segmentationinstance average mIoU: 85.3 -> 86.0Improved
Use 8 × 8 beams rather than 32 × 32 beams (ablation)RCNet · ModelNet40accuracy: 91.6 -> 87.5Hurt
Use 16 × 16 beams rather than 32 × 32 beams (ablation)RCNet · ModelNet40accuracy: 91.6 -> 90.2Hurt
Use 64 × 64 beams rather than 32 × 32 beams (ablation)RCNet · ModelNet40accuracy: 91.6 -> 90.9Hurt
Use 128 × 128 beams rather than 32 × 32 beams (ablation)RCNet · ModelNet40accuracy: 91.6 -> 89.8Hurt
Add random point dropout during training (ablation)RCNet · ModelNet40, 1024 pointsaccuracy: 90.2 -> 91.1Improved
Add random point dropout during training (ablation)RCNet · ModelNet40, 512 pointsaccuracy: 76.2 -> 90.4Improved
Add random point dropout during training (ablation)RCNet · ModelNet40, 256 pointsaccuracy: 38.1 -> 90.2Improved
Add random point dropout during training (ablation)RCNet · ModelNet40, 128 pointsaccuracy: 24.9 -> 87.8Improved

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