AI Paper Atlas

Research map / Label-efficient and robust learning / Test-time adaptation

Memory-Supported Synergistic Adaptation for Training-Free Test-Time Medical Image Segmentation

Lingrui Li, Nan Pu, Dong Zhao, Wenjing Li, Andrew French, Xin Chen, Zhun Zhong

ECCV 2026 · Label-efficient and robust learning › Test-time adaptation · approach: Test-time adaptation of vision-language models · 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
add SAM majority voting (ablation)MedCLIPv2 baseline · Optic disc ablation (avg)mIoU: 58.0 -> 61.8Improved
add attention-map majority voting (ablation)SAM-MV pipeline · Optic disc ablation (avg)mIoU: 61.8 -> 62.9Improved
add Gaussian point selection (ablation)SAM-MV + ATN-MV · Optic disc ablation (avg)mIoU: 62.9 -> 64.7Improved
add noise-aware memory construction with similar-anchor selection to full image-text branch (ablation)MSSA · Optic disc ablation (avg)mIoU: 64.7 -> 73.1Improved
add similarity-based anchor selection (ablation)MSSA without selection · Optic disc ablation (avg)mIoU: 70.8 -> 73.1Improved
self-referential image-image branch without image-text stabilization (add select) (ablation)Bank-only variant · Optic disc ablation (avg)mIoU: 67.0 -> 59.7Hurt
select anchor by similarity instead of random (ablation)MSSA · Optic disc anchor selection (avg)mIoU: 70.8 -> 73.1Improved
select anchor by similarity instead of semantic alignment (ablation)MSSA · Optic disc anchor selection (avg)DSC: 82.8 -> 83.9Improved
combine semantic and smoothness scores instead of Q_sem only (ablation)MSSA · Lung memory scoring (avg)DSC: 69.7 -> 78.4Improved
combine semantic and smoothness scores instead of Q_smo only (ablation)MSSA · Lung memory scoring (avg)DSC: 69.9 -> 78.4Improved
apply training-based TTA (TENT/EATA/CoTTA/DELTA) to VLM segmentationMedCLIPv2 · Optic disc, 5 domains avgDSC: 71.4 -> 71.0No clear effect
apply UniVPT TTAMedCLIPv2 · Optic disc, 5 domains avgDSC: 71.4 -> 67.1Hurt

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