AI Paper Atlas

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

MetaTeacher: Coordinating Multi-Model Domain Adaptation for Medical Image Classification

Zhenbin Wang, Mao Ye, Xiatian Zhu, Liuhan Peng, Liang Tian, Yingying Zhu

NeurIPS 2022 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Conditional distribution alignment · 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 coordinating weight learning (vs averaging teachers) (ablation)MetaTeacher · NIH-CXR14+CheXpert+MIMIC-CXR -> Open-iAUROC (average): 90.76 -> 92.84Improved
add bilevel optimization of teachers and student (ablation)MetaTeacher · NIH-CXR14+CheXpert+MIMIC-CXR -> Open-iAUROC (average): 89.32 -> 92.84Improved
add coordinating weight learning (vs averaging teachers) (ablation)MetaTeacher · NIH-CXR14+CheXpert+MIMIC-CXR -> Google-Health-CXRAUROC (average): 80.35 -> 82.69Improved
add bilevel optimization of teachers and student (ablation)MetaTeacher · NIH-CXR14+CheXpert+MIMIC-CXR -> Google-Health-CXRAUROC (average): 79.08 -> 82.69Improved
add coordinating weight learning (vs averaging teachers) (ablation)MetaTeacher · CheXpert+MIMIC-CXR -> NIH-CXR14AUROC (average): 76.16 -> 77.74Improved
add bilevel optimization of teachers and student (ablation)MetaTeacher · CheXpert+MIMIC-CXR -> NIH-CXR14AUROC (average): 75.16 -> 77.74Improved
add coordinating weight learning (vs averaging teachers) (ablation)MetaTeacher · NIH-CXR14+CheXpert -> Open-iAUROC (average): 90.72 -> 91.98Improved
add bilevel optimization of teachers and student (ablation)MetaTeacher · NIH-CXR14+CheXpert -> Open-iAUROC (average): 88.40 -> 91.98Improved
increase labeled target data from 50 to 200MetaTeacher · NIH-CXR14+CheXpert+MIMIC-CXR -> Open-iAUROC (average): 91.09 -> 92.84Improved
increase labeled target data from 200 to 300MetaTeacher · NIH-CXR14+CheXpert+MIMIC-CXR -> Open-iAUROC (average): 92.84 -> 92.97No clear effect
set beta to 0 (no mapping regularization) (ablation)MetaTeacher · NIH-CXR14+CheXpert+MIMIC-CXR -> Open-iAUROC (average): 92.84 -> 92.49Hurt
add divergence loss (gamma 0 -> 0.01) (ablation)MetaTeacher · NIH-CXR14+CheXpert+MIMIC-CXR -> Open-iAUROC (average): 92.29 -> 92.84Improved

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