{"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/practicaldg-perturbation-distillation-on","title":"PracticalDG: Perturbation Distillation on Vision-Language Models for Hybrid Domain Generalization","arxiv_id":"2404.09011","date":"2024-04-13","proceeding":"CVPR 2024 1","authors":["Zining Chen","Weiqiu Wang","Zhicheng Zhao","Fei Su","Aidong Men","Hongying Meng"],"abstract":"Domain Generalization (DG) aims to resolve distribution shifts between source and target domains, and current DG methods are default to the setting that data from source and target domains share identical categories. Nevertheless, there exists unseen classes from target domains in practical scenarios. To address this issue, Open Set Domain Generalization (OSDG) has emerged and several methods have been exclusively proposed. However, most existing methods adopt complex architectures with slight improvement compared with DG methods. Recently, vision-language models (VLMs) have been introduced in DG following the fine-tuning paradigm, but consume huge training overhead with large vision models. Therefore, in this paper, we innovate to transfer knowledge from VLMs to lightweight vision models and improve the robustness by introducing Perturbation Distillation (PD) from three perspectives, including Score, Class and Instance (SCI), named SCI-PD. Moreover, previous methods are oriented by the benchmarks with identical and fixed splits, ignoring the divergence between source domains. These methods are revealed to suffer from sharp performance decay with our proposed new benchmark Hybrid Domain Generalization (HDG) and a novel metric $H^{2}$-CV, which construct various splits to comprehensively assess the robustness of algorithms. Extensive experiments demonstrate that our method outperforms state-of-the-art algorithms on multiple datasets, especially improving the robustness when confronting data scarcity.","url_abs":"https://arxiv.org/abs/2404.09011v1","url_pdf":"https://arxiv.org/pdf/2404.09011v1.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":"practicaldg-perturbation-distillation-on","repo_url":"https://github.com/znchen666/hdg","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"domain-generalization","task_name":"Domain Generalization"}],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2404.09011","atlas_url":"https://app.syntology.ai/?focus=2404.09011","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.09011"}},"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/znchen666/hdg","reach":{"status":"ok","spdx":"GPL-3.0"}}],"summary":{"ran":2,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"repositories":1}},"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":3,"samples":[{"code_sha256_prefix":"fd70c42be97dc77c","entry":"accuracy","repo":"znchen666/hdg","repo_kind":"official","path":"alg/modelopera.py","file_url":"https://github.com/znchen666/hdg/blob/HEAD/alg/modelopera.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"fd70c42be97dc77c"}},{"code_sha256_prefix":"825e761a15944e3a","entry":"accuracy_per_class","repo":"znchen666/hdg","repo_kind":"official","path":"alg/modelopera.py","file_url":"https://github.com/znchen666/hdg/blob/HEAD/alg/modelopera.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"825e761a15944e3a"}},{"code_sha256_prefix":"e352afa5762c5a6b","entry":"calc_coeff","repo":"znchen666/hdg","repo_kind":"official","path":"network/util.py","file_url":"https://github.com/znchen666/hdg/blob/HEAD/network/util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"e352afa5762c5a6b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}