AI Paper Atlas

Research map / Point clouds / Segmentation and detection

Hierarchical Point-based Active Learning for Semi-supervised Point Cloud Semantic Segmentation

Zongyi Xu, Bo Yuan, Shanshan Zhao, Qianni Zhang, Xinbo Gao

ICCV 2023 · Point clouds › Segmentation and detection · approach: Point cloud semantic segmentation · 33 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 random point selection with hierarchical point-based active selection (HMMU + FDS) (ablation)Point-based active learning, MinkowskiNet · S3DIS Area 5 (0.1% labels)mIoU: 54.7 -> 59.3Improved
add hierarchical voxel-level contextual uncertainty (HMMU) to point-level MMU (ablation)Active learning module · S3DIS Area 5 (0.1% labels)mIoU: 55.51 -> 57.65Improved
add feature-distance suppression (FDS) to MMU selection (ablation)Active learning module · S3DIS Area 5 (0.1% labels)mIoU: 55.51 -> 56.68Improved
add teacher-student semi-supervised module on top of HMMU + FDS (ablation)Hierarchical point-based active learning · S3DIS Area 5 (0.1% labels)mIoU: 59.29 -> 62.26Improved
use entropy or least-confidence point selection instead of randomPoint-based active learning · S3DIS Area 5 (0.1% labels)mIoU: 54.7 -> 48.2 (Entropy), 53.3 (LC)Hurt
use point-based selection instead of region-based selection to reduce labellingActive learning · S3DIS Area 5labelled points for 90% of fully-supervised: 15% -> 0.1%Improved
use one point-level and three voxel-level layers in HMMU (ablation)HMMU · S3DIS Area 5 (0.1% labels)mIoU iter 5: 56.68 -> 59.29Improved
add a fourth voxel-level layer in HMMU (v_r=200cm) (ablation)HMMU · S3DIS Area 5 (0.1% labels)mIoU iter 5: 59.29 -> 59.19No clear effect
set FDS radius 20cm and threshold 0.8 rather than other combinations (ablation)FDS · S3DIS Area 5 (0.1% labels)mIoU iter 5: 58.79 -> 59.29Improved
use proposed method with 20 labelled points per scene versus GaIA on ScanNetV2Hierarchical point-based active learning · ScanNetV2 test (20 pts per scene)mIoU: 63.8 vs 62.5Hurt

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