AI Paper Atlas

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

MixStyle Neural Networks for Domain Generalization and Adaptation

Kaiyang Zhou, Yongxin Yang, Yu Qiao, Tao Xiang

IJCV 2023 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Optimization-based domain generalization · 209 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 MixStyle (random)ResNet-18 · PACS (DG, avg)accuracy: 79.5 -> 82.8Improved
add MixStyle (random) to Office-HomeResNet-18 · Office-Home (DG, avg)accuracy: 64.7 -> 65.5No clear effect
add MixStyle under DomainBedERM · Office-Home (DomainBed)accuracy: 67.6 -> 60.4Hurt
add MixStyle under DomainBedERM · PACS (DomainBed)accuracy: 84.2 -> 85.2Improved
add MixStyle (random)ResNet-50 · Market1501->Duke re-IDmAP: 19.3 -> 23.8Improved
add MixStyle to FixMatchFixMatch · VisDA-17 (UDA)accuracy: 77.1 -> 80.0Improved
add MixStyle to FixMatchFixMatch · PACS (multi-source UDA, avg)accuracy: 90.30 -> 92.55Improved
apply MixStyle after res1-3 instead of res1 (ablation)ResNet-18 · PACS (DG, avg)accuracy: 80.1 -> 82.8Improved
also apply MixStyle after res4 (all four blocks) (ablation)ResNet-18 · PACS (DG, avg)accuracy: 82.8 -> 75.6Hurt
apply MixStyle after res1-2 instead of res1-4 (ablation)ResNet-50 · Market1501->Duke re-IDmAP: 10.2 -> 23.8Improved
mix styles instead of replacing them (ablation)MixStyle · PACS (DG, avg)accuracy: 82.1 -> 82.8Improved
random shuffle at each layer instead of fixed shuffle (ablation)MixStyle · PACS (DG, avg)accuracy: 82.4 -> 82.8Improved

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