{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/deeper-broader-and-artier-domain","title":"Deeper, Broader and Artier Domain Generalization","arxiv_id":"1710.03077","date":"2017-10-09","proceeding":"ICCV 2017 10","authors":["Da Li","Yongxin Yang","Yi-Zhe Song","Timothy M. Hospedales"],"abstract":"The problem of domain generalization is to learn from multiple training\ndomains, and extract a domain-agnostic model that can then be applied to an\nunseen domain. Domain generalization (DG) has a clear motivation in contexts\nwhere there are target domains with distinct characteristics, yet sparse data\nfor training. For example recognition in sketch images, which are distinctly\nmore abstract and rarer than photos. Nevertheless, DG methods have primarily\nbeen evaluated on photo-only benchmarks focusing on alleviating the dataset\nbias where both problems of domain distinctiveness and data sparsity can be\nminimal. We argue that these benchmarks are overly straightforward, and show\nthat simple deep learning baselines perform surprisingly well on them. In this\npaper, we make two main contributions: Firstly, we build upon the favorable\ndomain shift-robust properties of deep learning methods, and develop a low-rank\nparameterized CNN model for end-to-end DG learning. Secondly, we develop a DG\nbenchmark dataset covering photo, sketch, cartoon and painting domains. This is\nboth more practically relevant, and harder (bigger domain shift) than existing\nbenchmarks. The results show that our method outperforms existing DG\nalternatives, and our dataset provides a more significant DG challenge to drive\nfuture research.","url_abs":"http://arxiv.org/abs/1710.03077v1","url_pdf":"http://arxiv.org/pdf/1710.03077v1.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":"deeper-broader-and-artier-domain","repo_url":"https://github.com/Evgeneus/Graph-Domain-Adaptaion","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deeper-broader-and-artier-domain","repo_url":"https://github.com/deeplearning-wisc/hypo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deeper-broader-and-artier-domain","repo_url":"https://github.com/facebookresearch/DomainBed","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deeper-broader-and-artier-domain","repo_url":"https://github.com/facebookresearch/ModelRatatouille","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deeper-broader-and-artier-domain","repo_url":"https://github.com/hlzhang109/ddg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deeper-broader-and-artier-domain","repo_url":"https://github.com/xch-liu/geom-tex-dg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"domain-generalization","task_name":"Domain Generalization"}],"methods":[],"datasets_introduced":[{"slug":"pacs","name":"PACS","full_name":"Photo-Art-Cartoon-Sketch"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/domain-generalization-on-pacs-2","task":"Domain Generalization","dataset":"PACS","model":"TF (Alexnet)","rank_in_archive_order":127,"of":133,"metrics":{"Average Accuracy":"69.21"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-pacs-2","task":"Domain Generalization","dataset":"PACS","model":"LRE-SVM","rank_in_archive_order":130,"of":133,"metrics":{"Average Accuracy":"58.99"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-pacs-2","task":"Domain Generalization","dataset":"PACS","model":"SVM","rank_in_archive_order":131,"of":133,"metrics":{"Average Accuracy":"58.74"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1710.03077","atlas_url":"https://app.syntology.ai/?focus=1710.03077","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.03077"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/DomainBed","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/deeplearning-wisc/hypo","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Evgeneus/Graph-Domain-Adaptaion","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hlzhang109/ddg","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/ModelRatatouille","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xch-liu/geom-tex-dg","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":3,"unverified":4},"by_repo_kind":{"listed":{"samples":7,"ran":3,"repositories":2}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"fac5364e2f53c6db","entry":"conv3x3","repo":"xch-liu/geom-tex-dg","repo_kind":"listed","path":"Dassl/dassl/modeling/backbone/resnet.py","file_url":"https://github.com/xch-liu/geom-tex-dg/blob/HEAD/Dassl/dassl/modeling/backbone/resnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fac5364e2f53c6db"}},{"code_sha256_prefix":"53fac8d8d949e72b","entry":"get_test_records","repo":"hlzhang109/ddg","repo_kind":"listed","path":"model_selection.py","file_url":"https://github.com/hlzhang109/ddg/blob/HEAD/model_selection.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"53fac8d8d949e72b"}},{"code_sha256_prefix":"c631ff42fed59f21","entry":"stage_path","repo":"hlzhang109/ddg","repo_kind":"listed","path":"scripts/download.py","file_url":"https://github.com/hlzhang109/ddg/blob/HEAD/scripts/download.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c631ff42fed59f21"}},{"code_sha256_prefix":"da48cf51668411a0","entry":"compute_accuracy","repo":"xch-liu/geom-tex-dg","repo_kind":"listed","path":"Dassl/dassl/metrics/accuracy.py","file_url":"https://github.com/xch-liu/geom-tex-dg/blob/HEAD/Dassl/dassl/metrics/accuracy.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"da48cf51668411a0"}},{"code_sha256_prefix":"cbff6e3d6b3109ac","entry":"compute_distance_matrix","repo":"xch-liu/geom-tex-dg","repo_kind":"listed","path":"Dassl/dassl/metrics/distance.py","file_url":"https://github.com/xch-liu/geom-tex-dg/blob/HEAD/Dassl/dassl/metrics/distance.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cbff6e3d6b3109ac"}},{"code_sha256_prefix":"e8878931ade705ee","entry":"cosine_distance","repo":"xch-liu/geom-tex-dg","repo_kind":"listed","path":"Dassl/dassl/metrics/distance.py","file_url":"https://github.com/xch-liu/geom-tex-dg/blob/HEAD/Dassl/dassl/metrics/distance.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e8878931ade705ee"}},{"code_sha256_prefix":"4dae6b1e21e10987","entry":"euclidean_squared_distance","repo":"xch-liu/geom-tex-dg","repo_kind":"listed","path":"Dassl/dassl/metrics/distance.py","file_url":"https://github.com/xch-liu/geom-tex-dg/blob/HEAD/Dassl/dassl/metrics/distance.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4dae6b1e21e10987"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}