{"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/partial-adversarial-domain-adaptation","title":"Partial Adversarial Domain Adaptation","arxiv_id":"1808.04205","date":"2018-08-10","proceeding":"ECCV 2018 9","authors":["Zhangjie Cao","Lijia Ma","Mingsheng Long","Jian-Min Wang"],"abstract":"Domain adversarial learning aligns the feature distributions across the\nsource and target domains in a two-player minimax game. Existing domain\nadversarial networks generally assume identical label space across different\ndomains. In the presence of big data, there is strong motivation of\ntransferring deep models from existing big domains to unknown small domains.\nThis paper introduces partial domain adaptation as a new domain adaptation\nscenario, which relaxes the fully shared label space assumption to that the\nsource label space subsumes the target label space. Previous methods typically\nmatch the whole source domain to the target domain, which are vulnerable to\nnegative transfer for the partial domain adaptation problem due to the large\nmismatch between label spaces. We present Partial Adversarial Domain Adaptation\n(PADA), which simultaneously alleviates negative transfer by down-weighing the\ndata of outlier source classes for training both source classifier and domain\nadversary, and promotes positive transfer by matching the feature distributions\nin the shared label space. Experiments show that PADA exceeds state-of-the-art\nresults for partial domain adaptation tasks on several datasets.","url_abs":"http://arxiv.org/abs/1808.04205v1","url_pdf":"http://arxiv.org/pdf/1808.04205v1.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":"partial-adversarial-domain-adaptation","repo_url":"https://github.com/thuml/PADA","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"partial-adversarial-domain-adaptation","repo_url":"https://github.com/thuml/Transfer-Learning-Library","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"partial-domain-adaptation","task_name":"Partial Domain Adaptation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/partial-domain-adaptation-on-domainnet","task":"Partial Domain Adaptation","dataset":"DomainNet","model":"PADA","rank_in_archive_order":3,"of":3,"metrics":{"Accuracy (%)":"37.41"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1808.04205","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1808.04205"}},"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/thuml/Transfer-Learning-Library","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/thuml/PADA","reach":null}],"summary":{"unverified":2},"by_repo_kind":{"official":{"samples":2,"ran":0,"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":2,"samples":[{"code_sha256_prefix":"55e5792a89e6f4e8","entry":"image_classification_predict","repo":"thuml/PADA","repo_kind":"official","path":"pytorch/src/train_pada.py","file_url":"https://github.com/thuml/PADA/blob/HEAD/pytorch/src/train_pada.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"55e5792a89e6f4e8"}},{"code_sha256_prefix":"f876454bcd479a54","entry":"image_classification_test","repo":"thuml/PADA","repo_kind":"official","path":"pytorch/src/train_pada.py","file_url":"https://github.com/thuml/PADA/blob/HEAD/pytorch/src/train_pada.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f876454bcd479a54"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}