AI Paper Atlas

Research map / Point clouds / Point cloud classification

Improving Adversarial Robustness of 3D Point Cloud Classification Models

Guanlin Li, Guowen Xu, Han Qiu, Ruan He, Jiwei Li, Tianwei Zhang

ECCV 2022 · Point clouds › Point cloud classification · approach: Adversarial point cloud attacks · 17 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
add CCN architecture on top of DGCNN, both trained with PointCutMix-K (ablation)DGCNN · ModelNet40 white-boxAAUA: 74.82 -> 76.35Improved
add CCN architecture on top of DGCNN, both trained with PointCutMix-K (ablation)DGCNN · ModelNet40 white-boxLAUA: 68.47 -> 68.30No clear effect
use CCN instead of PointNet, PointCutMix-K training (ablation)PointNet · ModelNet40 white-boxAAUA: 72.84 -> 76.35Improved
use receptive field alpha=4 instead of alpha=8 in CCM (ablation)CCN · ModelNet40 white-boxAAUA: 73.88 -> 76.35Improved
use receptive field alpha=4 instead of alpha=20 in CCM (ablation)CCN · ModelNet40 white-boxAAUA: 75.62 -> 76.35Improved
replace normal training by AMS (ablation)PointNet · ModelNet40 white-boxAAUA: 47.66 -> 77.44Improved
replace AT-BIM by AMS (T=0.5) (ablation)PointNet · ModelNet40 white-boxAAUA: 75.54 -> 77.44Improved
lower AMS threshold T from 0.5 to 0.1 (ablation)PointNet + AMS · ModelNet40 white-boxAAUA: 77.44 -> 71.03Hurt
replace PointCutMix-K by AMS on CCN (ablation)CCN · ModelNet40 white-boxAAUA: 76.35 -> 84.74Improved
replace PointCutMix-K by AMS on CCN (ablation)CCN · ModelNet40 white-boxLAUA: 68.30 -> 77.72Improved
replace AMS with AT-SMA on CCN (ablation)CCN · ModelNet40 white-boxSMA-40 accuracy: 77.72 -> 84.17Hurt
add AMS training to DGCNN instead of AT-BIMDGCNN · ModelNet40 white-boxAAUA: 78.76 -> 83.91Improved

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