AI Paper Atlas

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

Generalizable Decision Boundaries: Dualistic Meta-Learning for Open Set Domain Generalization

Xiran Wang, Jian Zhang, Lei Qi, Yinghuan Shi

ICCV 2023 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Foundation-model domain generalization · 40 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 class-wise gradient matching to domain-wise matching (MEDIC versus MLDG) with multi-binary classifier (ablation)MEDIC · PACS ResNet50H-score average: 79.9 -> 83.0Improved
add class-wise gradient matching to domain-wise matching (MEDIC versus MLDG) (ablation)MEDIC · PACS ResNet50OSCR average: 82.5 -> 84.9Improved
add multi-binary classifier to training and use it at inference (ablation)MEDIC · PACS ResNet50H-score average: 80.1 -> 83.0Improved
add multi-binary classifier to ERM (ablation)ERM · PACS ResNet50H-score average: 77.2 -> 79.9Improved
share parameters between close set and multi-binary classifier (ablation)MEDIC · PACS ResNet50H-score average: 83.0 -> 82.5No clear effect
use class-wise matching only without domain-wise matching (ablation)MEDIC · PACS ResNet50H-score average: 83.0 -> 80.3Hurt
MEDIC versus DAML on PACS ResNet18MEDIC · PACS ResNet18OSCR average: 73.69 -> 77.89Improved
MEDIC versus MVDG on PACS ResNet18MEDIC · PACS ResNet18OSCR average: 75.82 -> 77.89Improved
MEDIC versus SWAD on close set accuracyMEDIC · PACS ResNet50 close setaccuracy: 88.1 -> 88.3No clear effect
MEDIC versus MVDG close set accuracy on PACS ResNet18MEDIC · PACS ResNet18accuracy average: 86.41 -> 86.20Hurt

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