AI Paper Atlas

Research map / Point clouds / Point cloud classification

Verifiability and Predictability: Interpreting Utilities of Network Architectures for Point Cloud Processing

Wen Shen, Zhihua Wei, Shikun Huang, Binbin Zhang, Panyue Chen, Ping Zhao, Quanshi Zhang

CVPR 2021 · Point clouds › Point cloud classification · approach: Efficient point sampling architectures · 2 citations (OpenAlex)

Check 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
Keep Architecture 1, which reweights features using local density (ablation)PointConv · ModelNet40, ShapeNet, and 3D MNISTadversarial robustness: 0.249; 0.136; 0.207Improved
Keep Architecture 2, which reweights features using local coordinates (ablation)PointConv · ModelNet40, ShapeNet, and 3D MNISTrotation non-robustness: 0.191; 0.898; 1.369Improved
Increase Point2Sequence scales from 3 to 4 (ablation)Point2Sequence · ModelNet40, ShapeNet, and 3D MNISTadversarial robustness: 0.005; 0.006; -0.011Mixed
Increase Point2Sequence scales from 2 to 4 (ablation)Point2Sequence · ModelNet40, ShapeNet, and 3D MNISTadversarial robustness: 0.013; 0.032; 0.008Improved
Increase Point2Sequence scales from 3 to 4 (ablation)Point2Sequence · ModelNet40, ShapeNet, and 3D MNISTneighborhood inconsistency: 0.148; 0.177; 0.245Improved
Increase Point2Sequence scales from 2 to 4 (ablation)Point2Sequence · ModelNet40, ShapeNet, and 3D MNISTneighborhood inconsistency: -0.036; 0.132; 0.334Mixed
Keep Architecture 4, which encodes orientation-aware features (ablation)PointSIFT · ModelNet40, ShapeNet, and 3D MNISTrotation non-robustness: 3.343; 2.545; -0.689Mixed
Add Architecture 1PointNet++, Point2Sequence, and RSCNN · ModelNet40adversarial robustness: 0.015; 0.018; 0.028Improved
Add Architecture 1Point2Sequence · ShapeNetadversarial robustness: -0.020Hurt
Add Architecture 2PointNet++ and Point2Sequence · ModelNet40rotation non-robustness: 3.248; 4.543Improved
Add Architecture 2RSCNN · ModelNet40 and ShapeNetrotation non-robustness: -0.348; -1.225Hurt
Add Architecture 3PointNet++ and RSCNN · ModelNet40adversarial robustness: 0.506; 0.036Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 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