AI Paper Atlas

Research map / Point clouds / Point cloud classification

SK-Net: Deep Learning on Point Cloud via End-to-End Discovery of Spatial Keypoints

Weikun Wu, Yan Zhang, David Wang, Yunqi Lei

AAAI 2020 · Point clouds › Point cloud classification · approach: Local feature aggregation networks · 57 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
Use concatenated detail and pattern features instead of either feature alone (ablation)SK-Net · ModelNet10accuracy: 93.9\% (detail only), 93.3\% (pattern only) -> 95.8\%Improved
Add separation loss to classification loss without close loss (ablation)SK-Net · ModelNet10accuracy: 94.3\% -> 93.8\%Hurt
Add close loss to classification loss without separation loss (ablation)SK-Net · ModelNet10accuracy: 94.3\% -> 93.2\%Hurt
Add both separation and close losses (ablation)SK-Net · ModelNet10accuracy: 94.3\% -> 95.8\%; 1.5\%Improved
Replace kNN with ball query (ablation)SK-Net · ModelNet10accuracy: 95.8\% -> 94.3\% (r=0.1); 94.7\% (r=0.2)Hurt
Replace kNN with sift query (ablation)SK-Net · ModelNet10accuracy: 95.8\% -> 92.5\% (r=0.1); 92.7\% (r=0.2)Hurt
Use task-jointly learned Skeypoints rather than FPS- or SOM-derived keypoints (ablation)SK-Net · ModelNet10accuracyImproved
Use SK-Net rather than the strongest reported baselineSK-Net · ModelNet10class accuracy: 95.5 -> 96.2Improved
Use SK-Net rather than the strongest reported baselineSK-Net · ModelNet40instance accuracy: 93.4 -> 92.7Hurt
Use SK-Net rather than Point2SequenceSK-Net · ShapeNetPartmean IoU: 85.2 -> 85.0Hurt
Use SK-Net rather than PointNet++ (msg)SK-Net · ScanNetper-point accuracy: 83.2\% -> 81.4\%Hurt
Test with 50% of input points missingSK-Net · ModelNet10 and ModelNet40accuracy: drops by 3.4\% and 4.5\%, respectivelyHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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