Papers › Reducing Domain Gap by Reducing Style Bias

Reducing Domain Gap by Reducing Style Bias

25 Oct 2019CVPR 2021 1arXiv:1910.11645archive 2025-07-28

Hyeonseob Nam, Hyunjae Lee, Jongchan Park, Wonjun Yoon, Donggeun Yoo

Convolutional Neural Networks (CNNs) often fail to maintain their performance when they confront new test domains, which is known as the problem of domain shift. Recent studies suggest that one of the main causes of this problem is CNNs' strong inductive bias towards image styles (i.e. textures) which are sensitive to domain changes, rather than contents (i.e. shapes). Inspired by this, we propose to reduce the intrinsic style bias of CNNs to close the gap between domains. Our Style-Agnostic Networks (SagNets) disentangle style encodings from class categories to prevent style biased predictions and focus more on the contents. Extensive experiments show that our method effectively reduces the style bias and makes the model more robust under domain shift. It achieves remarkable performance improvements in a wide range of cross-domain tasks including domain generalization, unsupervised domain adaptation, and semi-supervised domain adaptation on multiple datasets.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

facebookresearch/DomainBed mentioned on GitHubpytorch report
hyeonseobnam/sagnet mentioned on GitHubpytorch report
hyeonseobnam/style-agnostic-networks mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Domain AdaptationDomain GeneralizationImage to sketch recognitionInductive BiasSemi-supervised Domain AdaptationSingle-Source Domain GeneralizationUnsupervised Domain Adaptation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Domain Generalization Office-Home SagNet (ResNet-18) Average Accuracy 62.34 #44 of 45 Archive leaderboard report
Domain Generalization PACS SagNet (Resnet-18) Average Accuracy 83.25 #71 of 133 Archive leaderboard report
Domain Generalization PACS SagNet (Resnet-50) Average Accuracy 82.3 #79 of 133 Archive leaderboard report
Domain Generalization PACS SagNet (Alexnet) Average Accuracy 75.52 #104 of 133 Archive leaderboard report
Image to sketch recognition PACS SagNet (ResNet18) Accuracy 40.7 #6 of 7 Archive leaderboard report
Single-Source Domain Generalization PACS SagNet (ResNet18) Accuracy 61.9 #9 of 10 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Test

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections