{"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/rethinking-multi-domain-generalization-with-a","title":"Rethinking Multi-domain Generalization with A General Learning Objective","arxiv_id":"2402.18853","date":"2024-02-29","proceeding":"CVPR 2024 1","authors":["Zhaorui Tan","Xi Yang","Kaizhu Huang"],"abstract":"Multi-domain generalization (mDG) is universally aimed to minimize the discrepancy between training and testing distributions to enhance marginal-to-label distribution mapping. However, existing mDG literature lacks a general learning objective paradigm and often imposes constraints on static target marginal distributions. In this paper, we propose to leverage a $Y$-mapping to relax the constraint. We rethink the learning objective for mDG and design a new \\textbf{general learning objective} to interpret and analyze most existing mDG wisdom. This general objective is bifurcated into two synergistic amis: learning domain-independent conditional features and maximizing a posterior. Explorations also extend to two effective regularization terms that incorporate prior information and suppress invalid causality, alleviating the issues that come with relaxed constraints. We theoretically contribute an upper bound for the domain alignment of domain-independent conditional features, disclosing that many previous mDG endeavors actually \\textbf{optimize partially the objective} and thus lead to limited performance. As such, our study distills a general learning objective into four practical components, providing a general, robust, and flexible mechanism to handle complex domain shifts. Extensive empirical results indicate that the proposed objective with $Y$-mapping leads to substantially better mDG performance in various downstream tasks, including regression, segmentation, and classification.","url_abs":"https://arxiv.org/abs/2402.18853v2","url_pdf":"https://arxiv.org/pdf/2402.18853v2.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":"rethinking-multi-domain-generalization-with-a","repo_url":"https://github.com/zhaorui-tan/gmdg","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"rethinking-multi-domain-generalization-with-a","repo_url":"https://github.com/zhaorui-tan/GMDG_cvpr2024","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"domain-generalization","task_name":"Domain Generalization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/domain-generalization-on-domainnet","task":"Domain Generalization","dataset":"DomainNet","model":"GMDG (RegNetY-16GF, SWAD)","rank_in_archive_order":8,"of":38,"metrics":{"Average Accuracy":"61.3"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-domainnet","task":"Domain Generalization","dataset":"DomainNet","model":"GMDG (RegNetY-16GF)","rank_in_archive_order":18,"of":38,"metrics":{"Average Accuracy":"54.6"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-domainnet","task":"Domain Generalization","dataset":"DomainNet","model":"GMDG (ResNet-50, SWAD)","rank_in_archive_order":26,"of":38,"metrics":{"Average Accuracy":"47.3"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-domainnet","task":"Domain Generalization","dataset":"DomainNet","model":"GMDG (ResNet-50)","rank_in_archive_order":32,"of":38,"metrics":{"Average Accuracy":"44.6"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-office-home","task":"Domain Generalization","dataset":"Office-Home","model":"GMDG (RegNetY-16GF, SWAD)","rank_in_archive_order":7,"of":45,"metrics":{"Average Accuracy":"84.7"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-office-home","task":"Domain Generalization","dataset":"Office-Home","model":"GMDG (RegNetY-16GF)","rank_in_archive_order":14,"of":45,"metrics":{"Average Accuracy":"80.8"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-office-home","task":"Domain Generalization","dataset":"Office-Home","model":"GMDG (ResNet-50, SWAD)","rank_in_archive_order":24,"of":45,"metrics":{"Average Accuracy":"72.5"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-office-home","task":"Domain Generalization","dataset":"Office-Home","model":"GMDG (ResNet-50)","rank_in_archive_order":29,"of":45,"metrics":{"Average Accuracy":"70.7"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-pacs-2","task":"Domain Generalization","dataset":"PACS","model":"GMDG (RegNetY-16GF, SWAD)","rank_in_archive_order":3,"of":133,"metrics":{"Average Accuracy":"97.9"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-pacs-2","task":"Domain Generalization","dataset":"PACS","model":"GMDG (e RegNetY-16GF)","rank_in_archive_order":6,"of":133,"metrics":{"Average Accuracy":"97.3"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-pacs-2","task":"Domain Generalization","dataset":"PACS","model":"GMDG (ResNet-50, SWAD)","rank_in_archive_order":29,"of":133,"metrics":{"Average Accuracy":"88.4"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-pacs-2","task":"Domain Generalization","dataset":"PACS","model":"GMDG (ResNet-50)","rank_in_archive_order":50,"of":133,"metrics":{"Average Accuracy":"85.6"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-terraincognita","task":"Domain Generalization","dataset":"TerraIncognita","model":"GMDG (RegNetY-16GF, SWAD)","rank_in_archive_order":2,"of":30,"metrics":{"Average Accuracy":"65"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-terraincognita","task":"Domain Generalization","dataset":"TerraIncognita","model":"GMDG (RegNetY-16GF)","rank_in_archive_order":6,"of":30,"metrics":{"Average Accuracy":"60.7"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-terraincognita","task":"Domain Generalization","dataset":"TerraIncognita","model":"GMDG (ResNet-50, SWAD)","rank_in_archive_order":15,"of":30,"metrics":{"Average Accuracy":"53.0"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-terraincognita","task":"Domain Generalization","dataset":"TerraIncognita","model":"GMDG (ResNet-50)","rank_in_archive_order":21,"of":30,"metrics":{"Average Accuracy":"51.1"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-vlcs","task":"Domain Generalization","dataset":"VLCS","model":"GMDG (RegNetY-16GF)","rank_in_archive_order":10,"of":37,"metrics":{"Average Accuracy":"82.4"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-vlcs","task":"Domain Generalization","dataset":"VLCS","model":"GMDG (RegNetY-16GF, SWAD)","rank_in_archive_order":15,"of":37,"metrics":{"Average Accuracy":"82.2"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-vlcs","task":"Domain Generalization","dataset":"VLCS","model":"GMDG (ResNet-50, SWAD)","rank_in_archive_order":25,"of":37,"metrics":{"Average Accuracy":"79.6"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-vlcs","task":"Domain Generalization","dataset":"VLCS","model":"GMDG (ResNet-50)","rank_in_archive_order":28,"of":37,"metrics":{"Average Accuracy":"79.2"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2402.18853","atlas_url":"https://app.syntology.ai/?focus=2402.18853","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":"2402.18853"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2402.18853\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2402.18853"},"call":"get_concepts_for_paper(arxiv_id=\"2402.18853\")"}],"by_repo":[{"repo":"zhaorui-tan/gmdg","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"zhaorui-tan/GMDG_cvpr2024","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":"dd40801c31ef0349db029b6e13dac0d78a3f6f474022b9d6db23beb3926eced9","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}