{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/reducing-domain-gap-via-style-agnostic","title":"Reducing Domain Gap by Reducing Style Bias","arxiv_id":"1910.11645","date":"2019-10-25","proceeding":"CVPR 2021 1","authors":["Hyeonseob Nam","Hyunjae Lee","Jongchan Park","Wonjun Yoon","Donggeun Yoo"],"abstract":"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.","url_abs":"https://arxiv.org/abs/1910.11645v4","url_pdf":"https://arxiv.org/pdf/1910.11645v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"reducing-domain-gap-via-style-agnostic","repo_url":"https://github.com/facebookresearch/DomainBed","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"reducing-domain-gap-via-style-agnostic","repo_url":"https://github.com/hyeonseobnam/sagnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"reducing-domain-gap-via-style-agnostic","repo_url":"https://github.com/hyeonseobnam/style-agnostic-networks","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"domain-generalization","task_name":"Domain Generalization"},{"task_slug":"image-to-sketch-recognition","task_name":"Image to sketch recognition"},{"task_slug":"inductive-bias","task_name":"Inductive Bias"},{"task_slug":"semi-supervised-domain-adaptation","task_name":"Semi-supervised Domain Adaptation"},{"task_slug":"single-source-domain-generalization","task_name":"Single-Source Domain Generalization"},{"task_slug":"unsupervised-domain-adaptation","task_name":"Unsupervised Domain Adaptation"}],"methods":[{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/domain-generalization-on-office-home","task":"Domain Generalization","dataset":"Office-Home","model":"SagNet (ResNet-18)","rank_in_archive_order":44,"of":45,"metrics":{"Average Accuracy":"62.34"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-pacs-2","task":"Domain Generalization","dataset":"PACS","model":"SagNet (Resnet-18)","rank_in_archive_order":71,"of":133,"metrics":{"Average Accuracy":"83.25"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-pacs-2","task":"Domain Generalization","dataset":"PACS","model":"SagNet (Resnet-50)","rank_in_archive_order":79,"of":133,"metrics":{"Average Accuracy":"82.3"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-pacs-2","task":"Domain Generalization","dataset":"PACS","model":"SagNet (Alexnet)","rank_in_archive_order":104,"of":133,"metrics":{"Average Accuracy":"75.52"},"uses_additional_data":false},{"leaderboard":"/sota/image-to-sketch-recognition-on-pacs","task":"Image to sketch recognition","dataset":"PACS","model":"SagNet (ResNet18)","rank_in_archive_order":6,"of":7,"metrics":{"Accuracy":"40.7"},"uses_additional_data":false},{"leaderboard":"/sota/single-source-domain-generalization-on-pacs","task":"Single-Source Domain Generalization","dataset":"PACS","model":"SagNet (ResNet18)","rank_in_archive_order":9,"of":10,"metrics":{"Accuracy":"61.9"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1910.11645","atlas_url":"https://app.syntology.ai/?focus=1910.11645","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1910.11645"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1910.11645\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1910.11645"},"call":"get_concepts_for_paper(arxiv_id=\"1910.11645\")"}],"by_repo":[{"repo":"facebookresearch/DomainBed","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":11,"harvested_for":["1505.07818","1512.03385","1607.01719","1907.02893","1911.08731","2003.00688","2007.01434","2011.09468","2106.03632","2106.07847","2201.00057"],"harvested_for_calls":[{"arxiv_id":"1505.07818","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1505.07818"},"call":"get_harvested_code_for_paper(arxiv_id=\"1505.07818\")"},{"arxiv_id":"1512.03385","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1512.03385"},"call":"get_harvested_code_for_paper(arxiv_id=\"1512.03385\")"},{"arxiv_id":"1607.01719","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1607.01719"},"call":"get_harvested_code_for_paper(arxiv_id=\"1607.01719\")"},{"arxiv_id":"1907.02893","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1907.02893"},"call":"get_harvested_code_for_paper(arxiv_id=\"1907.02893\")"},{"arxiv_id":"1911.08731","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1911.08731"},"call":"get_harvested_code_for_paper(arxiv_id=\"1911.08731\")"},{"arxiv_id":"2003.00688","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2003.00688"},"call":"get_harvested_code_for_paper(arxiv_id=\"2003.00688\")"},{"arxiv_id":"2007.01434","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2007.01434"},"call":"get_harvested_code_for_paper(arxiv_id=\"2007.01434\")"},{"arxiv_id":"2011.09468","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2011.09468"},"call":"get_harvested_code_for_paper(arxiv_id=\"2011.09468\")"},{"arxiv_id":"2106.03632","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2106.03632"},"call":"get_harvested_code_for_paper(arxiv_id=\"2106.03632\")"},{"arxiv_id":"2106.07847","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2106.07847"},"call":"get_harvested_code_for_paper(arxiv_id=\"2106.07847\")"},{"arxiv_id":"2201.00057","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2201.00057"},"call":"get_harvested_code_for_paper(arxiv_id=\"2201.00057\")"}]},{"repo":"hyeonseobnam/sagnet","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"hyeonseobnam/style-agnostic-networks","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"447c2503e4f7f0c8a0f82e7e81375aeae12bf1045e1233385734df54f37fbe5e","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}