AI Paper Atlas

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

Test-time Adaptation for Foundation Medical Segmentation Model Without Parametric Updates

Kecheng Chen, Xinyu Luo, Tiexin Qin, Jie Liu, Hui Liu, Victor Ho Fun Lee, Hong Yan, Haoliang Li

ICCV 2025 · Label-efficient and robust learning › Test-time adaptation · approach: Test-time adaptation of vision-language models · 1 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 DAL-CRF loss to latent refinement (ablation)MedSAM latent refinement · Fundus OD segmentation, loose promptsDice: 85.95 -> 89.88Improved
add entropy minimization loss alone (ablation)MedSAM direct inference · Fundus OD segmentation, loose promptsDice: 85.95 -> 86.01No clear effect
add entropy loss on top of DAL-CRF (ablation)MedSAM latent refinement · Fundus OD segmentation, loose promptsDice: 89.88 -> 90.14Improved
use DenseCRF post-processing (ablation)MedSAM direct inference · Fundus OD segmentation, loose promptsDice: 85.95 -> 79.18Hurt
swap DAL-CRF for InTEnt loss in latent framework (ablation)latent refinement · Fundus OD segmentation, loose promptsDice: 89.88 -> 84.78Hurt
swap DAL-CRF for TENT loss in latent framework (ablation)latent refinement · Fundus OD segmentation, loose promptsDice: 89.88 -> 86.28Hurt
swap DAL-CRF for CRF-SOD loss in latent framework (ablation)latent refinement · Fundus OD segmentation, loose promptsDice: 89.88 -> 87.71Hurt
increase K from 2 to 4 (ablation)latent refinement · Fundus OD segmentation, loose promptsDice: 89.75 -> 90.14Improved
increase K from 4 to 6 (ablation)latent refinement · Fundus OD segmentation, loose promptsDice: 90.14 -> 90.37Improved
increase K from 6 to 8 (ablation)latent refinement · Fundus OD segmentation, loose promptsDice: 90.37 -> 90.03Hurt
latent refinement instead of normalization update (TENT)MedSAM · Fundus OC segmentation, loose promptsDice: 85.89 -> 89.02Improved
latent refinement instead of best baselineMedSAM · Fundus OC segmentation, shrinkage promptsDice: 75.19 -> 77.77Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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