AI Paper Atlas

Research map / Label-efficient and robust learning / Semi-supervised learning

Instance Consistency Regularization for Semi-Supervised 3D Instance Segmentation

Yizheng Wu, Zhiyu Pan, Kewei Wang, Xingyi Li, Jiahao Cui, Liwen Xiao, Guosheng Lin, Zhiguo Cao

TPAMI 2024 · Label-efficient and robust learning › Semi-supervised learning · approach: Consistency training for semi-supervised segmentation · 7 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
use instance consistency only instead of joint consistency (ablation)InsTeacher3D · ScanNetV2 val (20% labels)mAP: 41.8 -> 42.7Improved
add semantic pseudo labels on top of instance consistency (semantic only vs instance only) (ablation)InsTeacher3D · ScanNetV2 val (20% labels)mAP: 42.7 -> 41.1Hurt
add mean teacher to the TWIST-style self-training (ablation)serial model · ScanNetV2 val (20% labels)mAP: 32.8 -> 39.0Improved
replace serial model with parallel DKNet (ablation)JCR with mean teacher · ScanNetV2 val (20% labels)mAP: 39.0 -> 41.8Improved
replace sem2ins serial model with ins2sem serial model (ablation)serial JCR · ScanNetV2 val (20% labels)mAP: 39.0 -> 34.7Hurt
add superpoint refinement to dynamic mask generation (ablation)InsTeacher3D · ScanNetV2 val (20% labels)mAP: 37.9 -> 41.4Improved
add instance self-enhancement to dynamic mask generation (ablation)InsTeacher3D · ScanNetV2 val (20% labels)AP50: 55.6 -> 57.0Improved
add both self-enhancement and superpoint refinement (ablation)InsTeacher3D · ScanNetV2 val (20% labels)mAP: 37.9 -> 42.7Improved
use EMA alpha 0.999 instead of 0.99 (ablation)mean teacher · ScanNetV2 val (20% labels)mAP: 39.4 -> 42.7Improved
use EMA alpha 0.9999 instead of 0.999 (ablation)mean teacher · ScanNetV2 val (20% labels)mAP: 42.7 -> 42.0No clear effect
choose centroids by heatmap score instead of randomly (ablation)DKNet · ScanNetV2 val (20% labels)mAP: 39.5 -> 42.7Improved
use centroid distance matching instead of IoU matching (ablation)DKNet · ScanNetV2 val (20% labels)mAP: 40.9 -> 42.7Improved

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