AI Paper Atlas

Research map / Point clouds / Point cloud classification

TopAdapter: Topology-Aware Prompt Tuning for Efficient Point Cloud Understanding

Changshuo Wang, Shuting He, Xiang Fang, Weijun Li, Yixian Shen, Mingkun Xu, Zhongtian Sun, Prayag Tiwari

ICML 2026 · Point clouds › Point cloud classification · approach: Self-supervised point cloud pretraining

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 Topology Injection module (ToInjection) alone (ablation)PointGPT-L · ScanObjectNN PB_T50_RSaccuracy (%): 93.40 -> 94.26Improved
add Topology Transfer module (ToTransfer) alone (ablation)PointGPT-L · ScanObjectNN PB_T50_RSaccuracy (%): 93.40 -> 94.13Improved
combine ToInjection and ToTransfer (ablation)TopAdapter on PointGPT-L · ScanObjectNN PB_T50_RSaccuracy (%): 94.26 -> 94.97Improved
add 0D, 1D and 2D simplex features over no simplex (ablation)TopAdapter on PointGPT-L · ScanObjectNN PB_T50_RSaccuracy (%): 93.62 -> 94.97Improved
use two simplex dimensions instead of one (ablation)TopAdapter on PointGPT-L · ScanObjectNN PB_T50_RSaccuracy (%): 94.21 -> 94.61Improved
set geometric control parameter alpha to 0.6 (ablation)TopAdapter on PointGPT-L · ScanObjectNN PB_T50_RSaccuracy (%): 94.28 (alpha 0.1) -> 94.97 (alpha 0.6) -> 94.52 (alpha 0.9)Mixed
set neighbor count K to 30 (ablation)TopAdapter on PointGPT-L · ScanObjectNN PB_T50_RSaccuracy (%): 93.82 (K=10) -> 94.97 (K=30)Mixed
apply TopAdapter instead of full fine-tuningPointGPT-L · ScanObjectNN PB_T50_RSaccuracy (%): 93.40 -> 94.97Improved
apply TopAdapter on ReCon for ShapeNetPart segmentationReCon · ShapeNetPartclass mIoU (%): 84.52 -> 83.99Hurt
apply TopAdapter on ReCon for ScanObjectNN PB_T50_RSReCon · ScanObjectNN PB_T50_RSaccuracy (%): 89.73 -> 89.82No clear effect
use general PEFT methods (Adapter, LoRA) instead of point-cloud-specific onesPoint-MAE · ScanObjectNN PB_T50_RSaccuracy (%): 81.74 (LoRA) vs 85.58 (TopAdapter)Hurt

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