{"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/butterfly-robust-one-step-approach-towards","title":"Butterfly: One-step Approach towards Wildly Unsupervised Domain Adaptation","arxiv_id":"1905.07720","date":"2019-05-19","proceeding":null,"authors":["Feng Liu","Jie Lu","Bo Han","Gang Niu","Guangquan Zhang","Masashi Sugiyama"],"abstract":"In unsupervised domain adaptation (UDA), classifiers for the target domain (TD) are trained with clean labeled data from the source domain (SD) and unlabeled data from TD. However, in the wild, it is difficult to acquire a large amount of perfectly clean labeled data in SD given limited budget. Hence, we consider a new, more realistic and more challenging problem setting, where classifiers have to be trained with noisy labeled data from SD and unlabeled data from TD -- we name it wildly UDA (WUDA). We show that WUDA ruins all UDA methods if taking no care of label noise in SD, and to this end, we propose a Butterfly framework, a powerful and efficient solution to WUDA. Butterfly maintains four deep networks simultaneously, where two take care of all adaptations (i.e., noisy-to-clean, labeled-to-unlabeled, and SD-to-TD-distributional) and then the other two can focus on classification in TD. As a consequence, Butterfly possesses all the conceptually necessary components for solving WUDA. Experiments demonstrate that, under WUDA, Butterfly significantly outperforms existing baseline methods.","url_abs":"https://arxiv.org/abs/1905.07720v3","url_pdf":"https://arxiv.org/pdf/1905.07720v3.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":"butterfly-robust-one-step-approach-towards","repo_url":"https://github.com/fengliu90/Butterfly","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"unsupervised-domain-adaptation","task_name":"Unsupervised Domain Adaptation"},{"task_slug":"wildly-unsupervised-domain-adaptation","task_name":"Wildly Unsupervised Domain Adaptation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/domain-adaptation-on-noisy-amazon-20","task":"Domain Adaptation","dataset":"Noisy-Amazon (20%)","model":"Butterfly","rank_in_archive_order":1,"of":1,"metrics":{"Average Accuracy":"71.53"},"uses_additional_data":false},{"leaderboard":"/sota/domain-adaptation-on-noisy-amazon-45","task":"Domain Adaptation","dataset":"Noisy-Amazon (45%)","model":"Butterfly","rank_in_archive_order":1,"of":1,"metrics":{"Average Accuracy":"56.01"},"uses_additional_data":false},{"leaderboard":"/sota/domain-adaptation-on-noisy-mnist-to-synd","task":"Domain Adaptation","dataset":"Noisy-MNIST-to-SYND","model":"Butterfly","rank_in_archive_order":1,"of":1,"metrics":{"Average Accuracy":"57.55"},"uses_additional_data":false},{"leaderboard":"/sota/domain-adaptation-on-noisy-synd-to-mnist","task":"Domain Adaptation","dataset":"Noisy-SYND-to-MNIST","model":"Butterfly","rank_in_archive_order":1,"of":1,"metrics":{"Average Accuracy":"94.09"},"uses_additional_data":false},{"leaderboard":"/sota/wildly-unsupervised-domain-adaptation-on-2","task":"Wildly Unsupervised Domain Adaptation","dataset":"Noisy-Amazon (20%)","model":"Butterfly","rank_in_archive_order":1,"of":1,"metrics":{"Average Accuracy":"71.53"},"uses_additional_data":false},{"leaderboard":"/sota/wildly-unsupervised-domain-adaptation-on-3","task":"Wildly Unsupervised Domain Adaptation","dataset":"Noisy-Amazon (45%)","model":"Butterfly","rank_in_archive_order":1,"of":1,"metrics":{"Average Accuracy":"56.01"},"uses_additional_data":false},{"leaderboard":"/sota/wildly-unsupervised-domain-adaptation-on","task":"Wildly Unsupervised Domain Adaptation","dataset":"Noisy-MNIST-to-SYND","model":"Butterfly","rank_in_archive_order":1,"of":1,"metrics":{"Average Accuracy":"57.55"},"uses_additional_data":false},{"leaderboard":"/sota/wildly-unsupervised-domain-adaptation-on-1","task":"Wildly Unsupervised Domain Adaptation","dataset":"Noisy-SYND-to-MNIST","model":"Butterfly","rank_in_archive_order":1,"of":1,"metrics":{"Average Accuracy":"94.09"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1905.07720","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.07720"}},"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/fengliu90/Butterfly","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":3},"by_repo_kind":{"listed":{"samples":3,"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":0,"samples":[{"code_sha256_prefix":"f9f0ffb2a5381fbe","entry":"return_Amazon","repo":"fengliu90/Butterfly","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/fengliu90/Butterfly/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f9f0ffb2a5381fbe"}},{"code_sha256_prefix":"e31d3391e5613f52","entry":"return_Obj_data","repo":"fengliu90/Butterfly","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/fengliu90/Butterfly/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e31d3391e5613f52"}},{"code_sha256_prefix":"160ca18353e10810","entry":"return_svhn","repo":"fengliu90/Butterfly","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/fengliu90/Butterfly/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"160ca18353e10810"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}