AI Paper Atlas

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

The Devil is in the Statistics: Mitigating and Exploiting Statistics Difference for Generalizable Semi-supervised Medical Image Segmentation

Muyang Qiu, Jian Zhang, Lei Qi, Qian Yu, Yinghuan Shi, Yang Gao

ECCV 2024 · Label-efficient and robust learning › Semi-supervised learning · approach: Semi-supervised medical segmentation · 6 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 statistics-individual and aggregated branches (SIAB) (ablation)semi-supervised DG baseline · Fundusaverage Dice (%): 83.28 -> 84.56Improved
add histogram-matching style augmentation (ablation)baseline with SIAB · Fundusaverage Dice (%): 84.56 -> 85.22Improved
add RandBN feature-level perturbation (ablation)SIAB + Style · Fundusaverage Dice (%): 85.22 -> 85.60Improved
use both batch and instance statistics in aggregated branch instead of one (ablation)SAB · Fundusaverage Dice (%): 83.50 -> 84.56Improved
use instance statistics only instead of batch statistics (ablation)SAB · Fundusaverage Dice (%): 83.50 -> 83.31Hurt
use strong plus style augmentation instead of two strong augmentations (ablation)consistency regularization · Fundusaverage Dice (%): 84.76 -> 85.60Improved
increase RandBN feature-consistency weight above 0.2 to 1.0 (ablation)Ours · Fundusaverage Dice (%): 85.60 -> 85.50No clear effect
apply RandBN perturbation (p>0) versus none (ablation)Ours · Fundusaverage Dice (%): 85.18 -> 85.63Improved
reduce training to 2.01 hours (ablation)Ours · Prostate (30%)Dice (%): 88.73 -> 87.98 (CACPS 86.47)No clear effect
vary confidence threshold from 0.85 to 0.99 (ablation)Ours · Fundusaverage Dice (%): 85.30 - 85.60No clear effect
apply method to typical semi-supervised task with 5% labelsOurs · ACDC 3 casesDice (%): BCP 87.59 vs Ours 86.72No clear effect

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