AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Multi-Channel Uncertainty-Weighted Score Matching for Conditional Diffusion in Medical UDA

CHEN LI, Meilong Xu, Xiaoling Hu, Weimin Lyu, Chao Chen

ECCV 2026 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Cross-modality medical segmentation adaptation

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 multi-channel uncertainty-weighted score matching for CDM training (ablation)Ours-PL · BraTS (T2->T1CE)Dice (avg, %): 52.88 -> 58.16Improved
add pixel-wise high-confidence collapse threshold (ablation)Ours-PL · BraTS (T2->T1CE)Dice (avg, %): 48.66 -> 58.16Improved
add CDM-generated labeled target images to pseudo-labeling (ablation)mean-teacher pseudo-labeling · BraTS (T2->T1CE)Dice (avg, %): 52.55 -> 58.16Improved
add real source images to generated data for segmenter training (ablation)Ours-PL · BraTS (T2->T1CE)Dice (avg, %): 49.51 -> 58.16Improved
use two ranked confidence maps (k=2) instead of one (ablation)UPDiff-UDA · BraTS (T2->T1CE)Dice (avg, %): 52.88 -> 58.16Improved
replace random Bezier curve with feature-guided Bezier adaptation (ablation)initial segmenter · BraTS (T2->T1CE)Dice (x10^2): 41.88 -> 48.45Improved
replace histogram matching with Bezier adaptation (ablation)initial segmenter · BraTS (T2->T1CE)Dice (x10^2): 11.98 -> 48.45Improved
use Bezier adaptation instead of CyCADA style transfer end-to-end (ablation)UPDiff-UDA · BraTS (T2->T1CE)Dice (avg, %): 48.76 -> 58.16Improved
raise confidence threshold delta from 0.7 to 0.8 (vs 0.9) (ablation)Ours-PL · BraTS (T2->T1CE)Dice (avg, %): 54.10 -> 58.16Improved
use ResNet34 instead of ResNet18 backbone (ablation)Ours-PL · BraTS (T2->T1CE)Dice (avg, %): 53.46 -> 58.16Improved
use ResNet50 instead of ResNet34 backbone (ablation)Ours-PL · BraTS (T2->T1CE)Dice (avg, %): 58.16 -> 57.17No clear effect
add generated target data to ADVENTADVENT · Abdominal Multi-Organ (MRI->CT)Dice (avg, %): 44.08 -> 82.38Improved

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