{"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/simple-specialized-model-sample-matching-for","title":"SIMPLE: Specialized Model-Sample Matching for Domain Generalization","arxiv_id":null,"date":"2023-05-01","proceeding":"International Conference on Learning Representations 2023 5","authors":["Ziyue Li","Kan Ren","Xinyang Jiang","Yifei Shen","Haipeng Zhang","Dongsheng Li"],"abstract":"In domain generalization (DG), most existing methods aspire to fine-tune a specific pretrained model through novel DG algorithms. In this paper, we propose an alternative direction, i.e., to efficiently leverage a pool of pretrained models without fine-tuning. Through extensive empirical and theoretical evidence, we demonstrate that (1) pretrained models have possessed generalization to some extent while there is no single best pretrained model across all distribution shifts, and (2) out-of-distribution (OOD) generalization error depends on the fitness between the pretrained model and unseen test distributions. This analysis motivates us to incorporate diverse pretrained models and to dispatch the best matched models for each OOD sample by means of recommendation techniques. To this end, we propose SIMPLE, a specialized model-sample matching method for domain generalization. First, the predictions of pretrained models are adapted to the target domain by a linear label space transformation. A matching network aware of model specialty is then proposed to dynamically recommend proper pretrained models to predict each test sample. The experiments on DomainBed show that our method achieves significant performance improvements (up to 12.2% for individual dataset and 3.9% on average) compared to state-of-the-art (SOTA) methods and further achieves 6.1% gain via enlarging the pretrained model pool. Moreover, our method is highly efficient and achieves more than 1000 times training speedup compared to the conventional DG methods with fine-tuning a pretrained model. Code and supplemental materials are available at https://seqml.github.io/simple.","url_abs":"https://openreview.net/forum?id=BqrPeZ_e5P","url_pdf":"https://openreview.net/pdf?id=BqrPeZ_e5P","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":"simple-specialized-model-sample-matching-for","repo_url":"https://github.com/microsoft/SeqML/tree/main/SIMPLE","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"domain-generalization","task_name":"Domain Generalization"},{"task_slug":"model","task_name":"model"}],"methods":[{"method_slug":"aware","method_name":"AWARE"},{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/domain-generalization-on-domainnet","task":"Domain Generalization","dataset":"DomainNet","model":"SIMPLE+","rank_in_archive_order":7,"of":38,"metrics":{"Average Accuracy":"61.9"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-domainnet","task":"Domain Generalization","dataset":"DomainNet","model":"SIMPLE","rank_in_archive_order":23,"of":38,"metrics":{"Average Accuracy":"49.2"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-office-home","task":"Domain Generalization","dataset":"Office-Home","model":"SIMPLE+","rank_in_archive_order":4,"of":45,"metrics":{"Average Accuracy":"87.7"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-office-home","task":"Domain Generalization","dataset":"Office-Home","model":"SIMPLE","rank_in_archive_order":8,"of":45,"metrics":{"Average Accuracy":"84.6"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-pacs-2","task":"Domain Generalization","dataset":"PACS","model":"SIMPLE+","rank_in_archive_order":1,"of":133,"metrics":{"Average Accuracy":"99.0"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-pacs-2","task":"Domain Generalization","dataset":"PACS","model":"SIMPLE","rank_in_archive_order":27,"of":133,"metrics":{"Average Accuracy":"88.6"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-terraincognita","task":"Domain Generalization","dataset":"TerraIncognita","model":"SIMPLE+","rank_in_archive_order":7,"of":30,"metrics":{"Average Accuracy":"59.0"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-terraincognita","task":"Domain Generalization","dataset":"TerraIncognita","model":"SIMPLE","rank_in_archive_order":9,"of":30,"metrics":{"Average Accuracy":"57.6"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-vlcs","task":"Domain Generalization","dataset":"VLCS","model":"SIMPLE+","rank_in_archive_order":8,"of":37,"metrics":{"Average Accuracy":"82.7"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-vlcs","task":"Domain Generalization","dataset":"VLCS","model":"SIMPLE","rank_in_archive_order":20,"of":37,"metrics":{"Average Accuracy":"79.9"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"no_arxiv_id","checked_against":null,"by_repo":[{"repo":"microsoft/SeqML","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2402.10635"],"harvested_for_calls":[{"arxiv_id":"2402.10635","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2402.10635"},"call":"get_harvested_code_for_paper(arxiv_id=\"2402.10635\")"}]}],"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":"5d4fc917ae823cc8aac6a30af55dda6faa78fe16ac7e7ce04be4456beb9603aa","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}