AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Better than Average: Spatially-Aware Aggregation of Segmentation Uncertainty Improves Downstream Performance

Vanessa Emanuela Guarino, Claudia Winklmayr, Jannik Franzen, Josef Lorenz Rumberger, Manuel Pfeuffer, Sonja Greven, Klaus Maier-Hein, Dagmar Kainmueller, Christoph Karg, Carsten T. Lüth

CVPR 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Interactive and referring segmentation · 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 prediction-based aggregation (BCA/ICA) instead of global averageuncertainty aggregation · OoD detection, 10 datasetsAUROCImproved
use meta-aggregator GMM-All instead of global averageuncertainty aggregation · OoD detection, 10 datasetsAUROCImproved
use global average (AVG) on LIDC-Maluncertainty aggregation · LIDC-Mal OoDAUROCImproved
use GMM-based meta-aggregators on Lizard (LIZ-IG/SG)GMM-All/Spa/Int · LIZ-IG, LIZ-SG OoDAUROCHurt
use above-threshold average (ATA) for OoD detectionuncertainty aggregation · OoD detection, 10 datasetsAUROCHurt
use ATA for failure detectionuncertainty aggregation · WORM-Nem, ARC-Nuc FDE-AURCImproved
use QFR (foreground-ratio quantile) instead of BCA/ICA for failure detectionuncertainty aggregation · Failure detection, 10 datasetsE-AURCImproved
add spatial features (GMM-All) to intensity-only features (GMM-Int) (ablation)GMM meta-aggregator · OoD detection and FDAUROC / E-AURCImproved
use GMM-All with all aggregators instead of single or leave-one-out features (ablation)GMM-All · CAR-CS, LIZ-IG, WEED-Hand, WORM-NemAUROCMixed
use global average (AVG) for failure detectionuncertainty aggregation · Failure detection, 10 datasetsE-AURCHurt

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