{"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/exploiting-domain-specific-features-to","title":"Exploiting Domain-Specific Features to Enhance Domain Generalization","arxiv_id":"2110.09410","date":"2021-10-18","proceeding":"NeurIPS 2021 12","authors":["Manh-Ha Bui","Toan Tran","Anh Tuan Tran","Dinh Phung"],"abstract":"Domain Generalization (DG) aims to train a model, from multiple observed source domains, in order to perform well on unseen target domains. To obtain the generalization capability, prior DG approaches have focused on extracting domain-invariant information across sources to generalize on target domains, while useful domain-specific information which strongly correlates with labels in individual domains and the generalization to target domains is usually ignored. In this paper, we propose meta-Domain Specific-Domain Invariant (mDSDI) - a novel theoretically sound framework that extends beyond the invariance view to further capture the usefulness of domain-specific information. Our key insight is to disentangle features in the latent space while jointly learning both domain-invariant and domain-specific features in a unified framework. The domain-specific representation is optimized through the meta-learning framework to adapt from source domains, targeting a robust generalization on unseen domains. We empirically show that mDSDI provides competitive results with state-of-the-art techniques in DG. A further ablation study with our generated dataset, Background-Colored-MNIST, confirms the hypothesis that domain-specific is essential, leading to better results when compared with only using domain-invariant.","url_abs":"https://arxiv.org/abs/2110.09410v1","url_pdf":"https://arxiv.org/pdf/2110.09410v1.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":"exploiting-domain-specific-features-to","repo_url":"https://github.com/vinairesearch/mdsdi","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"domain-generalization","task_name":"Domain Generalization"},{"task_slug":"meta-learning","task_name":"Meta-Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2110.09410","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.09410"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/vinairesearch/mdsdi","reach":null}],"summary":{"ran":3,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":5,"ran":4,"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":0,"samples":[{"code_sha256_prefix":"5e4bc9e4b4b65626","entry":"Domain_Discriminator","repo":"vinairesearch/mdsdi","repo_kind":"official","path":"DomainBed/domainbed/algorithms.py","file_url":"https://github.com/vinairesearch/mdsdi/blob/HEAD/DomainBed/domainbed/algorithms.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5e4bc9e4b4b65626"}},{"code_sha256_prefix":"ebff29d9d1f6869c","entry":"GradReverse","repo":"vinairesearch/mdsdi","repo_kind":"official","path":"DomainBed/domainbed/algorithms.py","file_url":"https://github.com/vinairesearch/mdsdi/blob/HEAD/DomainBed/domainbed/algorithms.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ebff29d9d1f6869c"}},{"code_sha256_prefix":"89eab76de8db596a","entry":"ZS_Domain_Classifier","repo":"vinairesearch/mdsdi","repo_kind":"official","path":"DomainBed/domainbed/algorithms.py","file_url":"https://github.com/vinairesearch/mdsdi/blob/HEAD/DomainBed/domainbed/algorithms.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"89eab76de8db596a"}},{"code_sha256_prefix":"4fa2b54178fcc1df","entry":"random_pairs_of_minibatches","repo":"vinairesearch/mdsdi","repo_kind":"official","path":"DomainBed/domainbed/algorithms.py","file_url":"https://github.com/vinairesearch/mdsdi/blob/HEAD/DomainBed/domainbed/algorithms.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4fa2b54178fcc1df"}},{"code_sha256_prefix":"6a8adc1a94a86cbf","entry":"MDSDI","repo":"vinairesearch/mdsdi","repo_kind":"official","path":"DomainBed/domainbed/algorithms.py","file_url":"https://github.com/vinairesearch/mdsdi/blob/HEAD/DomainBed/domainbed/algorithms.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6a8adc1a94a86cbf"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}