AI Paper Atlas

Research map / Point clouds / Segmentation and detection

Weakly Supervised 3D Scene Segmentation with Region-Level Boundary Awareness and Instance Discrimination

Kangcheng Liu, Yuzhi Zhao, Qiang Nie, Zhi Gao, Ben M. Chen

ECCV 2022 · 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
add boundary labels w_ij from boundary prediction network (ablation)WS3D · ScanNet instance seg val (5% labels)AP@50: 39.9 -> 45.6Improved
add pairwise term to the energy loss (ablation)WS3D · ScanNet instance seg val (5% labels)AP@50: 37.0 -> 45.6Improved
add confidence indicator H_ij in the energy function (ablation)WS3D · ScanNet instance seg val (5% labels)AP@50: 40.1 -> 45.6Improved
add confidence indicator H_ij in the contrastive loss (ablation)WS3D · ScanNet instance seg val (5% labels)AP@50: 40.7 -> 45.6Improved
apply contrastive learning at multiple stages instead of the fifth only (ablation)WS3D · ScanNet instance seg val (5% labels)AP@50: 42.2 -> 45.6Improved
add unsupervised region-level contrastive learning (ablation)WS3D · ScanNet instance seg val (5% labels)AP@50: 38.1 -> 45.6Improved
add supervised cross-entropy branch (ablation)WS3D · ScanNet instance seg val (5% labels)AP@50: 42.9 -> 45.6Improved
add unsupervised branch to supervised-only training (ablation)WS3D · ScanNet instance seg val (5% labels)AP@50: 34.8 -> 45.6Improved
add WS3D unlabeled-data losses to supervised-only GPC at 1% labelsSup-only-GPC · ScanNet val (1% labels)mIoU: 40.9 -> 49.9Improved
add WS3D losses to supervised-only PointGroup at 1% labelsSup-only-GPC · ScanNet instance seg val (1% labels)AP@50: 10.8 -> 32.5Improved
replace GPC with WS3D at 1% labelsGPC · S3DIS Area5 val (1% labels)mIoU: 38.2 -> 45.3Improved
add test set as unlabeled data (transductive learning)WS3D · ScanNet val (20% labels)mIoU: 68.5 -> 71.4Improved

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