AI Paper Atlas

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

You Point, I Learn: Online Adaptation of Interactive Segmentation Models for Handling Distribution Shifts in Medical Imaging

Wentian Xu, Ziyun Liang, Harry Anthony, Yasin Ibrahim, Felix Cohen, Guang Yang, Konstantinos Kamnitsas

ICLR 2026 · Label-efficient and robust learning › Test-time adaptation · approach: Test-time adaptation of vision-language models · 2 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 online adaptation (PI+MI) to a frozen interactive modelICNN* · BRATS T1 (Flair to T1), 10 clicksDice (%): 62.5 -> 88.0Improved
add Post-Interaction adaptation alone versus TSCAonline adaptation · ATLAS T1, 10 clicksDice (%): 64.0 -> 81.8Improved
add Mid-Interaction adaptation on top of Post-Interaction (ablation)PI · BRATS T1, 10 clicksDice (%): 78.9 -> 88.0Improved
add CCG loss to Dice-Focal loss in Mid-Interaction (ablation)PI+MI · BRATS T1, 10 clicksDice (%): 48.9 -> 88.0Improved
add Dice-Focal loss alongside CCG loss in Mid-Interaction (ablation)PI+MI · BRATS T1, 10 clicksDice (%): 86.8 -> 88.0Improved
add Post-Interaction adaptation when MI is already used, 5-click budget (ablation)MI · BRATS T2, 5 clicksDice (%): 89.8 -> 90.3Improved
add Post-Interaction when MI is already used, 10-click budget (ablation)MI · brain MRI, final clickDice (%)Mixed
add class-limited mechanism to CCG loss (ablation)PI+MI · ATLASDice (%): 80.7 -> 86.0Improved
use Gaussian kernel instead of uniform kernel in CCG loss (ablation)PI+MI · ATLASDice (%): 79.8 -> 86.0Improved
add CCG loss during pretraining of interactive model (ablation)interactive model · in-distribution and cross-distributionDice (%)Improved
increase click budget per image from 10 to 50 (ablation)TSCA · BRATS T1, early clicksDice (%): 34.4 -> 28.9 at click 1Hurt
use SAM-based Med-SA (frozen) instead of adapted U-NetMed-SA · BRATS T1, 10 clicksDice (%): 62.5 -> 35.7 versus ICNN*Hurt

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