AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Stabilizing In-Context Multi-Source Domain Adaptation for Biomedical Images Through Controls

Ana Sanchez-Fernandez, Thomas Pinetz, Werner Zellinger, Günter Klambauer

ICML 2026 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Statistical alignment and hypothesis testing · 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 negative controls to the BN adaptation context and meta-trainingARM-BN · label shift alpha=0.01accuracy: 0.228 -> 0.894Improved
add negative controls to the BN adaptation context and meta-trainingARM-BN · label shift alpha=0.1accuracy: 0.416 -> 0.906Improved
add negative controls to the BN adaptation contextARM-BN · mild shift, new batch (S3)accuracy: 0.935 -> 0.930No clear effect
add negative controls and meta-learningARM-BN · cross-source S3 -> S8accuracy: 0.874 -> 0.884Improved
add negative controls and meta-learningARM-BN · cross-source S8 -> S3accuracy: 0.795 -> 0.776Hurt
add negative controls at test time only (ablation)ARM-BN · label shift alpha=0.01, equal samplesaccuracy: 0.228 -> 0.752Improved
add control-aware meta-training on top of test-time controls (ablation)ARM-BN (perturbed + controls) · label shift alpha=0.01accuracy: 0.752 -> 0.894Improved
add meta-learning to control-only BN adaptation (ablation)BEN · S3 -> S8, alpha=0.01accuracy: 0.125 -> 0.663Improved
add perturbed samples to controls for BN statistics (ablation)ARM-BEN · S3 -> S8, alpha=0.01accuracy: 0.663 -> 0.825Improved
add entropy minimization on BN affine parameters (ablation)AdaBN · new batch, alpha=0.01accuracy: 0.229 -> 0.156Hurt
add test-time adaptation (AdaBN)ResNet50 BN · S3 -> S8 cross-sourceaccuracy: 0.670 -> 0.838Improved
add meta-learned in-context adaptation (ARM-BN) to small target batchAdaBN · smallest labeled batch sizeaccuracy: 0.130 -> 0.126No clear effect

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