AI Paper Atlas

Research map / Point clouds / Point cloud classification

PC-Adapter: Topology-Aware Adapter for Efficient Domain Adaption on Point Clouds with Rectified Pseudo-label

Joonhyung Park, Hyunjin Seo, Eunho Yang

ICCV 2023 · Point clouds › Point cloud classification · approach: Self-supervised point cloud pretraining · 14 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 locality-aware graph-convolution adapter to shape-aware adapter (ablation)PC-Adapter · PointDA-10 S->Maccuracy: 72.3 -> 75.7Improved
add beta distribution-guided pseudo-labeling (Beta PL) (ablation)PC-Adapter · PointDA-10 S->Maccuracy: 75.7 -> 77.5Improved
add beta distribution-guided pseudo-labeling (Beta PL) (ablation)PC-Adapter · PointDA-10 S*->Maccuracy: 68.2 -> 73.7Improved
use proposed relative positional encoding instead of conventional encoding (ablation)PC-Adapter · PointDA-10 S->Maccuracy: 74.2 -> 77.5Improved
use proposed relative positional encoding instead of conventional encoding (ablation)PC-Adapter · PointDA-10 S*->Maccuracy: 70.3 -> 73.7Improved
use beta-guided pseudo-labels instead of maximum confidence pseudo-labels (ablation)PC-Adapter · GraspNetPC-10 Syn.->RS.balanced accuracy: 67.93 -> 71.99Improved
use beta-guided pseudo-labels instead of maximum confidence pseudo-labels (ablation)PC-Adapter · GraspNetPC-10 Kin.->RS.balanced accuracy: 79.49 -> 83.52Improved
train on farthest-point-sampled data to remove local structure, no adaptation (ablation)PointNet and DGCNN · PointDA-10 multiple shiftsaccuracyImproved
PC-Adapter instead of best baseline on PointDA-10DGCNN · PointDA-10average accuracy: +5.3%Improved
PC-Adapter on part segmentation with locality-aware adapter onlyDGCNN · PointSegDAaverage mIoU: 60.0 -> 63.5Improved
PC-Adapter on GraspNetPC-10 Syn.->RS. when combined with ImplicitPCDAImplicitPCDA · GraspNetPC-10 Syn.->RS.accuracy: 80.5 -> 72.5Hurt
PC-Adapter instead of self-supervised baselines for training timePC-Adapter · ModelNet->ShapeNettraining speed: 3.43x fasterImproved

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