{"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/multi-adversarial-domain-adaptation","title":"Multi-Adversarial Domain Adaptation","arxiv_id":"1809.02176","date":"2018-09-04","proceeding":null,"authors":["Zhongyi Pei","Zhangjie Cao","Mingsheng Long","Jian-Min Wang"],"abstract":"Recent advances in deep domain adaptation reveal that adversarial learning\ncan be embedded into deep networks to learn transferable features that reduce\ndistribution discrepancy between the source and target domains. Existing domain\nadversarial adaptation methods based on single domain discriminator only align\nthe source and target data distributions without exploiting the complex\nmultimode structures. In this paper, we present a multi-adversarial domain\nadaptation (MADA) approach, which captures multimode structures to enable\nfine-grained alignment of different data distributions based on multiple domain\ndiscriminators. The adaptation can be achieved by stochastic gradient descent\nwith the gradients computed by back-propagation in linear-time. Empirical\nevidence demonstrates that the proposed model outperforms state of the art\nmethods on standard domain adaptation datasets.","url_abs":"http://arxiv.org/abs/1809.02176v1","url_pdf":"http://arxiv.org/pdf/1809.02176v1.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":"multi-adversarial-domain-adaptation","repo_url":"https://github.com/Darth-Kronos/Unsupervised-Domain-Adaptation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"multi-adversarial-domain-adaptation","repo_url":"https://github.com/MarvinMartin24/MADA-PL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"multi-adversarial-domain-adaptation","repo_url":"https://github.com/arthurdouillard/mada.pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"multi-adversarial-domain-adaptation","repo_url":"https://github.com/cht619/MADA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"multi-adversarial-domain-adaptation","repo_url":"https://github.com/MindCode-4/code-12/tree/main/multi-adversarial-domain-adaptation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"multi-adversarial-domain-adaptation","repo_url":"https://github.com/MindCode-4/code-7/tree/main/multi-adversarial-domain-adaptation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/domain-adaptation-on-office-31","task":"Domain Adaptation","dataset":"Office-31","model":"MADA","rank_in_archive_order":30,"of":40,"metrics":{"Average Accuracy":"85.2"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1809.02176","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1809.02176"}},"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/MarvinMartin24/MADA-PL","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/arthurdouillard/mada.pytorch","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Darth-Kronos/Unsupervised-Domain-Adaptation","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindCode-4/code-7/tree/main/multi-adversarial-domain-adaptation","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cht619/MADA","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindCode-4/code-12/tree/main/multi-adversarial-domain-adaptation","reach":null}],"summary":{"ran_honours":1},"by_repo_kind":{"listed":{"samples":1,"ran":1,"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":1,"samples":[{"code_sha256_prefix":"41b698897366cc58","entry":"inverseDecaySheduler","repo":"cht619/MADA","repo_kind":"listed","path":"train_functions/Optimizer_functions.py","file_url":"https://github.com/cht619/MADA/blob/HEAD/train_functions/Optimizer_functions.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"41b698897366cc58"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}