AI Paper Atlas

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

Adaptive Learning of High-Value Regions for Semi-Supervised Medical Image Segmentation

Tao Lei, Ziyao Yang, Xingwu Wang, Yi Wang, Xuan Wang, Feiman Sun, Asoke K. Nandi

ICCV 2025 · Label-efficient and robust learning › Semi-supervised learning · approach: Semi-supervised medical 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
add CG-CPCL on reliable unstable region (ablation)U-Net baseline · ACDC (10% labeled)Dice (%): 86.61 -> 89.32Improved
add DTCT on unreliable stable region (ablation)U-Net baseline · ACDC (10% labeled)Dice (%): 86.61 -> 89.19Improved
add DTCT to CG-CPCL (full ALHVR) (ablation)CG-CPCL · ACDC (10% labeled)Dice (%): 89.32 -> 90.56Improved
add CG-CPCL on reliable unstable region (ablation)U-Net baseline · AbdomenCT-1K (5% labeled)Dice (%): 79.19 -> 83.98Improved
add DTCT on unreliable stable region (ablation)U-Net baseline · AbdomenCT-1K (5% labeled)Dice (%): 79.19 -> 83.79Improved
add DTCT to CG-CPCL (full ALHVR) (ablation)CG-CPCL · AbdomenCT-1K (5% labeled)Dice (%): 83.98 -> 84.75Improved
add CG-CPCL on reliable unstable region (ablation)V-Net baseline · Brats (10% labeled)Dice (%): 83.20 -> 84.62Improved
add DTCT on unreliable stable region (ablation)V-Net baseline · Brats (10% labeled)Dice (%): 83.20 -> 84.85Improved
add DTCT to CG-CPCL (full ALHVR) (ablation)CG-CPCL · Brats (10% labeled)Dice (%): 84.62 -> 85.14Improved
set confidence-threshold proportion beta to 0.8 instead of 0.5 (ablation)ALHVR · ACDC (10% labeled)Dice (%): 89.88 -> 90.56Improved
set confidence-threshold proportion beta to 0.9 instead of 0.8 (ablation)ALHVR · ACDC (10% labeled)Dice (%): 90.56 -> 89.85Hurt
set beta to 0.7 instead of 0.5 (ablation)ALHVR · Brats (10% labeled)Dice (%): 84.71 -> 85.14Improved

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