{"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/cycada-cycle-consistent-adversarial-domain","title":"CyCADA: Cycle-Consistent Adversarial Domain Adaptation","arxiv_id":"1711.03213","date":"2017-11-08","proceeding":"ICML 2018 7","authors":["Judy Hoffman","Eric Tzeng","Taesung Park","Jun-Yan Zhu","Phillip Isola","Kate Saenko","Alexei A. Efros","Trevor Darrell"],"abstract":"Domain adaptation is critical for success in new, unseen environments.\nAdversarial adaptation models applied in feature spaces discover domain\ninvariant representations, but are difficult to visualize and sometimes fail to\ncapture pixel-level and low-level domain shifts. Recent work has shown that\ngenerative adversarial networks combined with cycle-consistency constraints are\nsurprisingly effective at mapping images between domains, even without the use\nof aligned image pairs. We propose a novel discriminatively-trained\nCycle-Consistent Adversarial Domain Adaptation model. CyCADA adapts\nrepresentations at both the pixel-level and feature-level, enforces\ncycle-consistency while leveraging a task loss, and does not require aligned\npairs. Our model can be applied in a variety of visual recognition and\nprediction settings. We show new state-of-the-art results across multiple\nadaptation tasks, including digit classification and semantic segmentation of\nroad scenes demonstrating transfer from synthetic to real world domains.","url_abs":"http://arxiv.org/abs/1711.03213v3","url_pdf":"http://arxiv.org/pdf/1711.03213v3.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":"cycada-cycle-consistent-adversarial-domain","repo_url":"https://github.com/jhoffman/cycada_release","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"cycada-cycle-consistent-adversarial-domain","repo_url":"https://github.com/thuml/Transfer-Learning-Library","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"cycada-cycle-consistent-adversarial-domain","repo_url":"https://github.com/tkhkaeio/CyCADA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"image-to-image-translation","task_name":"Image-to-Image Translation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"synthetic-to-real-translation","task_name":"Synthetic-to-Real Translation"},{"task_slug":"unsupervised-image-to-image-translation","task_name":"Unsupervised Image-To-Image Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/domain-adaptation-on-svhn-to-mnist","task":"Domain Adaptation","dataset":"SVHN-to-MNIST","model":"CYCADA","rank_in_archive_order":11,"of":14,"metrics":{"Accuracy":"90.4"},"uses_additional_data":false},{"leaderboard":"/sota/image-to-image-translation-on-synthia-fall-to","task":"Image-to-Image Translation","dataset":"SYNTHIA Fall-to-Winter","model":"CyCADA","rank_in_archive_order":1,"of":2,"metrics":{"Per-pixel Accuracy":"92.1%","fwIOU":"85.7","mIoU":"63.3"},"uses_additional_data":false},{"leaderboard":"/sota/synthetic-to-real-translation-on-gtav-to","task":"Synthetic-to-Real Translation","dataset":"GTAV-to-Cityscapes Labels","model":"CyCADA pixel+feat","rank_in_archive_order":67,"of":73,"metrics":{"Per-pixel Accuracy":"82.3%","fwIOU":"72.4","mIoU":"39.5"},"uses_additional_data":false},{"leaderboard":"/sota/synthetic-to-real-translation-on-gtav-to","task":"Synthetic-to-Real Translation","dataset":"GTAV-to-Cityscapes Labels","model":"CyCADA pixel-only","rank_in_archive_order":70,"of":73,"metrics":{"mIoU":"34.8"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-image-to-image-translation-on","task":"Unsupervised Image-To-Image Translation","dataset":"SVNH-to-MNIST","model":"CyCADA pixel+feat","rank_in_archive_order":1,"of":4,"metrics":{"Classification Accuracy":"90.4%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1711.03213","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.03213"}},"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/jhoffman/cycada_release","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tkhkaeio/CyCADA","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":2,"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":0,"samples":[{"code_sha256_prefix":"8fadf1baab2bb38b","entry":"register_model","repo":"jhoffman/cycada_release","repo_kind":"official","path":"cycada/models/models.py","file_url":"https://github.com/jhoffman/cycada_release/blob/HEAD/cycada/models/models.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"8fadf1baab2bb38b"}},{"code_sha256_prefix":"2efe87863253f8ba","entry":"get_model","repo":"jhoffman/cycada_release","repo_kind":"official","path":"cycada/models/models.py","file_url":"https://github.com/jhoffman/cycada_release/blob/HEAD/cycada/models/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"2efe87863253f8ba"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}