{"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/rda-robust-domain-adaptation-via-fourier","title":"RDA: Robust Domain Adaptation via Fourier Adversarial Attacking","arxiv_id":"2106.02874","date":"2021-06-05","proceeding":"ICCV 2021 10","authors":["Jiaxing Huang","Dayan Guan","Aoran Xiao","Shijian Lu"],"abstract":"Unsupervised domain adaptation (UDA) involves a supervised loss in a labeled source domain and an unsupervised loss in an unlabeled target domain, which often faces more severe overfitting (than classical supervised learning) as the supervised source loss has clear domain gap and the unsupervised target loss is often noisy due to the lack of annotations. This paper presents RDA, a robust domain adaptation technique that introduces adversarial attacking to mitigate overfitting in UDA. We achieve robust domain adaptation by a novel Fourier adversarial attacking (FAA) method that allows large magnitude of perturbation noises but has minimal modification of image semantics, the former is critical to the effectiveness of its generated adversarial samples due to the existence of 'domain gaps'. Specifically, FAA decomposes images into multiple frequency components (FCs) and generates adversarial samples by just perturbating certain FCs that capture little semantic information. With FAA-generated samples, the training can continue the 'random walk' and drift into an area with a flat loss landscape, leading to more robust domain adaptation. Extensive experiments over multiple domain adaptation tasks show that RDA can work with different computer vision tasks with superior performance.","url_abs":"https://arxiv.org/abs/2106.02874v3","url_pdf":"https://arxiv.org/pdf/2106.02874v3.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":"rda-robust-domain-adaptation-via-fourier","repo_url":"https://github.com/jxhuang0508/RDA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"unsupervised-domain-adaptation","task_name":"Unsupervised Domain Adaptation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2106.02874","atlas_url":"https://app.syntology.ai/?focus=2106.02874","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.02874"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/jxhuang0508/RDA","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":2,"ran_fixture":1,"ran_draft_wrong":1,"ran":2,"unverified":4},"by_repo_kind":{"listed":{"samples":10,"ran":6,"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":"21ac171a17099011","entry":"colorize_mask","repo":"jxhuang0508/RDA","repo_kind":"listed","path":"crst/deeplab/datasets_advent.py","file_url":"https://github.com/jxhuang0508/RDA/blob/HEAD/crst/deeplab/datasets_advent.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"21ac171a17099011"}},{"code_sha256_prefix":"90009a990acf6c4d","entry":"colorize_mask","repo":"jxhuang0508/RDA","repo_kind":"listed","path":"crst/evaluate_advent.py","file_url":"https://github.com/jxhuang0508/RDA/blob/HEAD/crst/evaluate_advent.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"90009a990acf6c4d"}},{"code_sha256_prefix":"fac5364e2f53c6db","entry":"conv3x3","repo":"jxhuang0508/RDA","repo_kind":"listed","path":"crst/deeplab/model_advent.py","file_url":"https://github.com/jxhuang0508/RDA/blob/HEAD/crst/deeplab/model_advent.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fac5364e2f53c6db"}},{"code_sha256_prefix":"b64838217324e413","entry":"l1_loss","repo":"jxhuang0508/RDA","repo_kind":"listed","path":"rda/domain_adaptation/train_UDA.py","file_url":"https://github.com/jxhuang0508/RDA/blob/HEAD/rda/domain_adaptation/train_UDA.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b64838217324e413"}},{"code_sha256_prefix":"27504cbeb5811ea6","entry":"outS","repo":"jxhuang0508/RDA","repo_kind":"listed","path":"crst/deeplab/model_advent.py","file_url":"https://github.com/jxhuang0508/RDA/blob/HEAD/crst/deeplab/model_advent.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"27504cbeb5811ea6"}},{"code_sha256_prefix":"3f1545c4d33dca0e","entry":"parse_split_list","repo":"jxhuang0508/RDA","repo_kind":"listed","path":"crst/crst_seg_advent.py","file_url":"https://github.com/jxhuang0508/RDA/blob/HEAD/crst/crst_seg_advent.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3f1545c4d33dca0e"}},{"code_sha256_prefix":"6599d0cc6e7549ee","entry":"Res_Ms_Deeplab","repo":"jxhuang0508/RDA","repo_kind":"listed","path":"crst/deeplab/model_advent.py","file_url":"https://github.com/jxhuang0508/RDA/blob/HEAD/crst/deeplab/model_advent.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":"6599d0cc6e7549ee"}},{"code_sha256_prefix":"b9a6f5d02f50c40a","entry":"colorize_mask","repo":"jxhuang0508/RDA","repo_kind":"listed","path":"crst/crst_seg_advent.py","file_url":"https://github.com/jxhuang0508/RDA/blob/HEAD/crst/crst_seg_advent.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":"b9a6f5d02f50c40a"}},{"code_sha256_prefix":"9546e8417b4bdc1a","entry":"grad_reverse","repo":"jxhuang0508/RDA","repo_kind":"listed","path":"rda/utils/gate.py","file_url":"https://github.com/jxhuang0508/RDA/blob/HEAD/rda/utils/gate.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":"9546e8417b4bdc1a"}},{"code_sha256_prefix":"043a52d8f9ff0f65","entry":"to_numpy","repo":"jxhuang0508/RDA","repo_kind":"listed","path":"rda/domain_adaptation/train_UDA.py","file_url":"https://github.com/jxhuang0508/RDA/blob/HEAD/rda/domain_adaptation/train_UDA.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":"043a52d8f9ff0f65"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}