AI Paper Atlas

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

Atlas is Your Perfect Context: One-Shot Customization for Generalizable Foundational Medical Image Segmentation

Ziyu Zhang, Yi Yu, Simeng Zhu, Ahmed Aly, Yunhe Gao, Ning Gu, Yuan Xue

ECCV 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Interactive and referring segmentation · 3 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
derive FM prompts from a registered atlas instead of oracle clicks (ablation)nnInteractive · HaN-SegDice: 42.42 -> 61.74Improved
add atlas-derived prompts to nnInteractive (ablation)nnInteractive · PengwinDice: 72.09 -> 94.56Improved
add adaptive fusion of atlas and FM predictions (ablation)AtlasSegFM · PengwinDice: 94.56 -> 95.50Improved
add adaptive fusion of atlas and FM predictions (ablation)AtlasSegFM · HaN-SegDice: 61.74 -> 63.71Improved
add fusion on top of vesselFM alone (ablation)vesselFM · Fe-MRADice: 55.28 -> 84.42Improved
add rigid pre-registration to atlas registration (ablation)atlas registration · PengwinDice: 63.24 -> 70.55Improved
add affine pre-registration after rigid (ablation)atlas registration · PengwinDice: 70.55 -> 82.75Improved
use mask prompt instead of box prompt from atlas (ablation)AtlasSegFM · PengwinDice: 88.96 -> 95.77Improved
use AtlasSegFM instead of Iris on organs-at-riskone-shot segmentation · BrainRT organs-at-riskDice: 10.45 -> 77.07Improved
AtlasSegFM versus 5-click nnInteractive on AVT vesselsAtlasSegFM · AVTDice: 83.38 -> 81.34Hurt
AtlasSegFM (MedSAM2-based) versus 5-click nnInteractive on HaN-SegAtlasSegFM · HaN-SegDice: 55.29 -> 52.61Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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