AI Paper Atlas

Research map / Point clouds / Point cloud classification

PointCert: Point Cloud Classification With Deterministic Certified Robustness Guarantees

Jinghuai Zhang, Jinyuan Jia, Hongbin Liu, Neil Zhenqiang Gong

CVPR 2023 · Point clouds › Point cloud classification · approach: Adversarial point cloud attacks · 9 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 deterministic disjoint hash-based sub-point clouds and majority voting instead of randomized smoothing or PointGuardPoint cloud classification on ModelNet40 · ModelNet40Certified accuracy@50: 79% vs. $0$Improved
Train the base classifier on sub-point clouds rather than standard point clouds (ablation)PointCert Scenario II vs. Scenario I · ModelNet40 and ScanObjectNN variantscertified accuracyImproved
Prepend a Point Completion Network before the standard-trained classifier (ablation)PointCert Scenario III vs. Scenario I · ModelNet40 and ScanObjectNN variantscertified accuracyImproved
Add the classifier-oriented loss term to PCN training (lambda > 0 rather than lambda = 0) (ablation)PointCert Scenario III · ModelNet40 and ScanObjectNN variantscertified accuracyImproved
Vary the number of hash-based sub-point clouds; smaller m raises clean accuracy but weakens robustness (ablation)PointCert Scenario II · ModelNet40certified accuracyMixed
Use MD5 rather than the mean-based hash function (ablation)PointCert Scenario II · ModelNet40certified accuracyImproved
Use different base point cloud classifiers (ablation)PointCert Scenario II · ModelNet40certified accuracyNo clear effect
Increase the PCN classification-loss weight lambda; certified accuracy rises and then falls (ablation)PointCert Scenario III · ModelNet40certified accuracyMixed
Use a pretrained PCN rather than training the PCN from scratch (ablation)PointCert Scenario III · ModelNet40certified accuracyImproved
Increase the fraction of customer point clouds with labels (ablation)PointCert Scenario III · ModelNet40certified accuracyImproved
Use knowledge-distilled student model in the black-box setting rather than the teacher model in the white-box setting (ablation)PointCert Scenario III · ModelNet40certified accuracyNo clear effect
Use PointGuard instead of PointCert under empirical point deletion attacksPoint cloud classification · ModelNet40 and ScanObjectNN variantsempirical accuracyImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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