AI Paper Atlas

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

Cross-Domain Ensemble Distillation for Domain Generalization

Kyungmoon Lee, Sungyeon Kim, Suha Kwak

ECCV 2022 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Optimization-based domain generalization · 46 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 XDED to vanilla ResNet-18 (ablation)ResNet-18 · PACS Art (multi-source)accuracy: 77.0 -> 83.3Improved
add UniStyle to vanilla ResNet-18 (ablation)ResNet-18 · PACS Art (multi-source)accuracy: 77.0 -> 81.2Improved
add UniStyle on top of XDED (ablation)XDED · PACS Art (multi-source)accuracy: 83.3 -> 85.6Improved
add XDED to vanilla ResNet-18 (ablation)ResNet-18 · OfficeHome Clipart (multi-source)accuracy: 49.4 -> 55.2Improved
add UniStyle to vanilla ResNet-18 (ablation)ResNet-18 · OfficeHome Clipart (multi-source)accuracy: 49.4 -> 50.4Improved
add UniStyle on top of XDED (ablation)XDED · OfficeHome Clipart (multi-source)accuracy: 55.2 -> 57.1Improved
add UniStyle to vanilla ResNet-50 re-ID (ablation)ResNet-50 · Market1501 to DukeMTMC-reIDmAP: 19.3 -> 26.2Improved
add XDED to vanilla ResNet-50 re-ID (ablation)ResNet-50 · Market1501 to DukeMTMC-reIDmAP: 19.3 -> 24.2Improved
add XDED + UniStyle in place of one-hot-only domain generalization baselines (MixStyle)ResNet-18 · PACS Cartoon entropyaccuracy: 75.9 -> 81.7Improved
add XDED + UniStyle versus ResNet-18 under FGSMResNet-18 · PACS Photo under FGSM attack (multi-source)accuracy: 39.6 -> 55.4Improved
add XDED + UniStyle versus ResNet-18 under PGDResNet-18 · PACS Photo under PGD attack (multi-source)accuracy: 16.3 -> 30.4Improved
add XDED + UniStyle versus Mixup on corruptionWRN-40-2 · CIFAR-10-Cclassification error: 22.3 -> 18.5Improved

Earlier methods this paper compares with

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