AI Paper Atlas

Research map / Point clouds / Segmentation and detection

Reliability-Adaptive Consistency Regularization for Weakly-Supervised Point Cloud Segmentation

Zhonghua Wu, Yicheng Wu, Guosheng Lin, Jianfei Cai

IJCV 2024 · Point clouds › Segmentation and detection · approach: Point cloud semantic segmentation · 30 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 the full RAC-Net adaptive consistency trainingKPConv baseline · S3DIS Area 5 (OTOC, 0.02% labels)mIoU (%): 50.1 -> 58.4Improved
use RAC-Net instead of DATweakly-supervised segmentation · S3DIS Area 5 (OTOC, 0.02% labels)mIoU (%): 56.5 -> 58.4Improved
use RAC-Net instead of DATweakly-supervised segmentation · S3DIS Area 5 (OTTC, 0.06% labels)mIoU (%): 58.5 -> 60.5Improved
apply RAC-Net on a voxel-based MinkowskiNet backboneMinkowskiNet baseline · S3DIS Area 5 (OTOC, MinkowskiNet backbone)mIoU (%): 48.7 -> 58.6Improved
add RAC-Net built on 1T1C pseudo labels1T1C · ScanNet-v2 test (20 points)mIoU (%): 59.4 -> 62.6Improved
add RAC-Net on Point Transformer backbonePoint Transformer baseline · ScanNet-v2 test (20 points)mIoU (%): 56.4 -> 63.9Improved
add the ambiguous-set KL consistency loss L_a (ablation)RAC-Net · S3DIS Area 5 (OTOC, 0.02% labels)mIoU (%): 52.5 -> 58.4Improved
add the reliable-pseudo-label mix loss L_mix (ablation)RAC-Net · S3DIS Area 5 (OTOC, 0.02% labels)mIoU (%): 57.6 -> 58.4Improved
add uncertainty to confidence for dividing reliable and ambiguous sets (ablation)RAC-Net · S3DIS Area 5 (OTOC, 0.02% labels)mIoU (%): 56.5 -> 57.6Improved
apply KL loss on the ambiguous set in confidence-based division (ablation)confidence-based pseudo labeling · S3DIS Area 5 (OTOC, 0.02% labels)mIoU (%): 55.8 -> 56.5Improved
add adaptive division of points over uniform consistency on all points (ablation)RAC-Net · S3DIS Area 5 (OTOC, 0.02% labels)mIoU (%): 56.7 -> 58.4Improved
use cross-entropy instead of Dice for the reliable set (ablation)RAC-Net · S3DIS Area 5 (OTOC, 0.02% labels)mIoU (%): 48.8 -> 58.4Improved

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