AI Paper Atlas

Research map / Point clouds / Point cloud classification

Adaptive Graph Convolution for Point Cloud Analysis

Haoran Zhou, Yidan Feng, Mingsheng Fang, Mingqiang Wei, Jing Qin, Tong Lu

ICCV 2021 · Point clouds › Point cloud classification · approach: Local feature aggregation networks · 211 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 adaptive kernels instead of standard graph convolution (ablation)AdaptConv · ShapeNetPartmcIoU: 81.9 -> 83.4Improved
use adaptive kernels instead of standard graph convolution (ablation)AdaptConv · ShapeNetPartmIoU: 85.5 -> 86.4Improved
use adaptive kernels instead of point attention weights (ablation)AdaptConv · ShapeNetPartmIoU: 83.3 -> 86.4Improved
use adaptive kernels instead of channel attention (ablation)AdaptConv · ShapeNetPartmIoU: 83.0 -> 86.4Improved
convolve kernel with xyz instead of previous-layer features (ablation)AdaptConv · ShapeNetPartmcIoU: 82.2 -> 83.4Improved
use xyz inputs instead of normals only (ablation)AdaptConv · ShapeNetPartmcIoU: 83.2 -> 83.4Improved
use xyz inputs instead of xyz plus normals (ablation)AdaptConv · ShapeNetPartmIoU: 86.1 -> 86.4No clear effect
increase neighborhood size k from 5 to 20 (ablation)AdaptConv · ModelNet40OA: 92.8 -> 93.4Improved
increase neighborhood size k from 20 to 40 (ablation)AdaptConv · ModelNet40OA: 93.4 -> 93.0Hurt
increase neighborhood size k from 10 to 20 (ablation)AdaptConv · ModelNet40OA: 93.2 -> 93.4No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 3 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