AI Paper Atlas

Research map / Point clouds / Segmentation and detection

One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation

Zhengzhe Liu, Xiaojuan Qi, Chi-Wing Fu

CVPR 2021 · Point clouds › Segmentation and detection · approach: Point cloud semantic segmentation · 156 citations (OpenAlex)

Check 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
Apply iterative self-training to initial pseudo labels (ablation)3D U-Net on ScanNet-v2 val · ScanNet-v2 valmIoU: 60.14 -> 65.91Improved
Add graph propagation with color and coordinate similarity (ablation)Self-trained 3D U-Net on ScanNet-v2 val · ScanNet-v2 valmIoU: 65.91 -> 67.92Improved
Add a relation network to graph similarity and use the memory bank for category prototypes (ablation)3D U-Net+GP on ScanNet-v2 val · ScanNet-v2 valmIoU: 67.92 -> 70.45Improved
Use current-minibatch prototypes instead of a memory bank (ablation)3D U-Net+Rel+GP on ScanNet-v2 val · ScanNet-v2 valmIoU: 67.98 -> 70.45Hurt
Use graph propagation and the relation network during inference (ablation)3D U-Net+Rel+GP on ScanNet-v2 val · ScanNet-v2 valmIoU: 69.12 -> 70.45Improved
Use self-training with one-point-per-object supervision instead of initial pseudo labels only (ablation)One Thing One Click on S3DIS Area 5 · S3DIS Area 5mIoU: 43.7 -> 50.1Improved
Use self-training with three points per object instead of initial pseudo labels only (ablation)One Thing Three Clicks on S3DIS Area 5 · S3DIS Area 5mIoU: 48.9 -> 55.3Improved
Annotate three points rather than one point per object (ablation)One Thing Click annotation scheme on S3DIS Area 5 · S3DIS Area 5mIoU: 50.1 -> 55.3Improved
Use only the initial pseudo labels instead of iterative self-training (ablation)One Thing One Click on ScanNet-v2 val · ScanNet-v2 valmIoU: 62.18 -> 70.45Hurt
Disable graph propagation and relation network during inference (ablation)One Thing One Click on ScanNet-v2 val · ScanNet-v2 valmIoU: 70.45 -> 68.96Hurt
Disable graph propagation and relation network during inference (ablation)One Thing One Click on S3DIS Area 5 · S3DIS Area 5mIoU: 50.1 -> 49.4Hurt
Disable graph propagation and relation network during inference (ablation)One Thing Three Clicks on S3DIS Area 5 · S3DIS Area 5mIoU: 55.3 -> 54.1Hurt

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