AI Paper Atlas

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

Unsupervised Source-Free Ranking of Biomedical Segmentation Models Under Distribution Shift

Joshua Talks, Kevin Marchesini, Luca Lumetti, Federico Bolelli, Anna Kreshuk

ECCV 2026 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Cross-modality medical segmentation adaptation · 0 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 CMR consistency ranking instead of unsupervised baseline TSCMR-EI (Gauss) · Mitochondria semantic segmentationKendall tau: 0.25 -> 0.77Improved
use CMR instead of classification-derived supervised metrics like NLEEPCMR-EI (Gauss) · Nuclei semantic segmentationKendall tau: 0.11 -> 0.62Improved
apply input Gaussian noise vs feature DropOut perturbation (ablation)CMR-EI · Mitochondria semantic segmentationKendall tau: 0.77 -> 0.73No clear effect
use hard NHD instead of soft EI consistency (ablation)CMR (Gauss) · ToothFairy2 overallKendall tau: 0.71 -> 0.90Improved
use CMR instead of TS on multi-class 3D segmentationCMR-NHD (Gamma) · ToothFairy2 overallKendall tau: 0.33 -> 1.00Improved
rank post-UDA models with CMR rather than Transfer Score (Mean Teacher)CMR-EI (Gauss) · Post-UDA EPFLKendall tau: 0.45 -> 0.78Improved
rank post-UDA models with CMR rather than TS (AdaBN)CMR-EI (Gauss) · Post-UDA EPFLKendall tau: 0.50 -> 0.70Improved
target VNC after Mean Teacher self-trainingCMR-EI (Gauss) · Post-UDA VNCKendall tau: 0.78 -> 0.21Hurt
use CMR-ARS instead of SEG for cell instance rankingCMR-ARS (DropOut) · Cell instance segmentationKendall tau: 0.12 -> 0.69Improved
use CMR-ARS instead of SEG for nuclei instance rankingCMR-ARS (DropOut) · Nuclei instance segmentationKendall tau: 0.48 -> 0.80Improved
vary Gaussian noise strength sigma from 0.01-0.03 to 0.10-0.12 (ablation)CMR-EI (Gauss) · Mitochondria EPFL targetKendall tau: 0.73 -> 0.87No clear effect
use a single perturbation per image rather than ~10 runs (ablation)CMR · semantic segmentation rankingcorrelationNo clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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