AI Paper Atlas

Research map / Point clouds / Point cloud classification

3D-ANC: Adaptive Neural Collapse for Robust 3D Point Cloud Recognition

Yuanmin Huang, Wenxuan Li, Mi Zhang, Xiaohan Zhang, Xiaoyu You, Min Yang

AAAI 2026 · Point clouds › Point cloud classification · approach: Adversarial point cloud attacks · 0 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
replace the classifier with a fixed simplex ETF head (ablation)PointNet · ModelNet40 (avg over 5 attacks)accuracy under attack: +38.1Improved
replace the classifier with a fixed simplex ETF head (ablation)PointNet · ModelNet40 (clean)clean accuracy: -0.6Hurt
add RBL (learnable rotation) to the ETF head (ablation)3D-ANC (ETF head) · ModelNet40 (clean)clean accuracy: -0.6 -> +3.7Improved
add RBL (learnable rotation) to the ETF head (ablation)3D-ANC (ETF head) · ModelNet40 (avg over 5 attacks)accuracy under attack: +38.1 -> +34.5Hurt
add FDL to the ETF head without RBL (ablation)3D-ANC (ETF head) · ModelNet40 (avg over 5 attacks)accuracy under attack: +38.1 -> +31.7Hurt
add FDL to the ETF head without RBL (ablation)3D-ANC (ETF head) · ModelNet40 (clean)clean accuracy: -0.6 -> -1.4Hurt
add FDL on top of ETF and RBL (ablation)3D-ANC (ETF & RBL) · ModelNet40 (avg over 5 attacks)accuracy under attack: +34.5 -> +39.3Improved
add FDL on top of ETF and RBL (ablation)3D-ANC (ETF & RBL) · ModelNet40 (clean)clean accuracy: +3.7 -> +0.9Hurt
apply 3D-ANC (ETF head, RBL, FDL)DGCNN · ModelNet40 (avg over 5 attacks)accuracy under attack: 27.2 -> 80.9Improved
apply 3D-ANC (ETF head, RBL, FDL)PCT · ModelNet40 (avg over 5 attacks)accuracy under attack: 47.5 -> 77.3Improved
apply 3D-ANC versus best baseline defense on shape-invariant attacksPointNet · ModelNet40 (shape-invariant attacks, avg)accuracy under attack: 54.9 -> 63.6Improved
apply 3D-ANC versus PointCutMix on HiT attackPointNet · ModelNet40 (HiT attack)accuracy: 73.7 -> 66.1Hurt

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