AI Paper Atlas

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

Episodic Training for Domain Generalization

Da Li, Jianshu Zhang, Yongxin Yang, Cong Liu, Yi-Zhe Song, Timothy M. Hospedales

ICCV 2019 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Foundation-model domain generalization · 445 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 episodic feature-extractor training (Epi-F) (ablation)AGG · PACS (AlexNet)accuracy (%): 1.6% boost over AGGImproved
add episodic classifier training (Epi-C) on top of Epi-F (ablation)Epi-F · PACS (AlexNet)accuracy (%): further improves 0.5%Improved
combine all episodic components (Epi-FCR) (ablation)AGG · PACS (AlexNet)accuracy (%): 3.3% improvement over vanilla AGGImproved
add Epi-FCR episodic trainingAGG · IXMASaccuracy (%): 90.6 -> 93.0Improved
add Epi-FCR episodic trainingAGG · VLCSaccuracy (%): 71.2 -> 72.9Improved
add Epi-FCR episodic trainingAGG · PACS (ResNet-18)accuracy (%): 79.1 -> 81.5Improved
add Epi-R random-classifier episodic trainingAGG (concat) · VD-DGaccuracy (%): 38.7 -> 39.7Improved
add Epi-R random-classifier episodic training (VD score)AGG (concat) · VD-DGVD score: 265 -> 304Improved
accumulate BN statistics from source domains instead of freezing ImageNet statisticsResNet-18 · PACSaccuracy (%): 79.1 -> 75.7Hurt
train episodic with ensemble of n+1 AGG models instead (compare) (ablation)Epi-FCR · PACS (ResNet-18)accuracy (%): 80.4 vs 81.5Improved
globally share first two blocks (S2B) (ablation)Epi-FCR · PACS (ResNet-18)accuracy (%): 79.1 -> 80.9No clear effect
split modules at intermediate layers (first/third block) (ablation)Epi-FCR · PACS (ResNet-18)accuracy (%): 81.5 -> 80.6Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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