Papers › Reducing Domain Gap by Reducing Style Bias
Reducing Domain Gap by Reducing Style Bias
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.
In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.
Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
For agents, on Syntology's MCP service (how to connect):
get_citation_path(paper_1="1910.11645", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="1910.11645")
Code
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.
A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 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
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