AI Paper Atlas

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

Single-Domain Generalization in Medical Image Segmentation via Test-Time Adaptation from Shape Dictionary

Quande Liu, Cheng Chen, Qi Dou, Pheng-Ann Heng

AAAI 2022 · Label-efficient and robust learning › Test-time adaptation · approach: Test-time adaptation of vision-language models · 44 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
Integrate a learned shape dictionary and dual-consistency test-time adaptationSingle-domain prostate MRI segmentation · Prostate MRI, unseen sites B–F averageDice: 78.2 -> 81.1Improved
Integrate a learned shape dictionary and dual-consistency test-time adaptationSingle-domain prostate MRI segmentation · Prostate MRI, unseen sites B–F averageHausdorff Distance: 41.0 -> 32.3Improved
Integrate a learned shape dictionary and dual-consistency test-time adaptationSingle-domain fundus segmentation · Fundus segmentation, unseen sites B–D averageDice: 84.6 -> 85.8Improved
Integrate a learned shape dictionary and dual-consistency test-time adaptationSingle-domain fundus segmentation · Fundus segmentation, unseen sites B–D averageHausdorff Distance: 22.3 -> 20.5Improved
Add integration of the shape dictionary to the baseline (ablation)Single-domain prostate MRI segmentation · Prostate MRI, unseen sites B–F averageDice: 74.8 -> 78.4Improved
Add integration of the shape dictionary to the baseline (ablation)Single-domain fundus segmentation · Fundus segmentation, unseen sites B–D averageDice: 82.7 -> 84.4Improved
Add test-time adaptation to the model with shape dictionary integration (ablation)Baseline + ISD · Prostate MRI, unseen sites B–F averageDice: +2.7%Improved
Add test-time adaptation to the model with shape dictionary integration (ablation)Baseline + ISD · Fundus segmentation, unseen sites B–D averageDice: +1.4%Improved
Use middle-sized dictionary (K=32 or 48) instead of K=16 or K=64 (ablation)TASD · Prostate MRI and fundus segmentationDiceImproved
Use fewer ground-truth masks to learn the shape dictionary (ablation)TASD · Prostate MRI segmentationDice: 0.7% and 1.6%Hurt
Use fewer ground-truth masks to learn the shape dictionary (ablation)TASD · Fundus segmentationDice: 0.4% and 0.9%Hurt
Add consistency regularization on shape coefficients (ablation)TASD test-time adaptation · Medical image segmentationSegmentation performanceImproved

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