{"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/lead-learning-decomposition-for-source-free","title":"LEAD: Learning Decomposition for Source-free Universal Domain Adaptation","arxiv_id":"2403.03421","date":"2024-03-06","proceeding":"CVPR 2024 1","authors":["Sanqing Qu","Tianpei Zou","Lianghua He","Florian Röhrbein","Alois Knoll","Guang Chen","Changjun Jiang"],"abstract":"Universal Domain Adaptation (UniDA) targets knowledge transfer in the presence of both covariate and label shifts. Recently, Source-free Universal Domain Adaptation (SF-UniDA) has emerged to achieve UniDA without access to source data, which tends to be more practical due to data protection policies. The main challenge lies in determining whether covariate-shifted samples belong to target-private unknown categories. Existing methods tackle this either through hand-crafted thresholding or by developing time-consuming iterative clustering strategies. In this paper, we propose a new idea of LEArning Decomposition (LEAD), which decouples features into source-known and -unknown components to identify target-private data. Technically, LEAD initially leverages the orthogonal decomposition analysis for feature decomposition. Then, LEAD builds instance-level decision boundaries to adaptively identify target-private data. Extensive experiments across various UniDA scenarios have demonstrated the effectiveness and superiority of LEAD. Notably, in the OPDA scenario on VisDA dataset, LEAD outperforms GLC by 3.5% overall H-score and reduces 75% time to derive pseudo-labeling decision boundaries. Besides, LEAD is also appealing in that it is complementary to most existing methods. The code is available at https://github.com/ispc-lab/LEAD.","url_abs":"https://arxiv.org/abs/2403.03421v1","url_pdf":"https://arxiv.org/pdf/2403.03421v1.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":"lead-learning-decomposition-for-source-free","repo_url":"https://github.com/ispc-lab/lead","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"lead-learning-decomposition-for-source-free","repo_url":"https://github.com/ispc-lab/glc","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":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"universal-domain-adaptation","task_name":"Universal Domain Adaptation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/universal-domain-adaptation-on-domainnet","task":"Universal Domain Adaptation","dataset":"DomainNet","model":"LEAD","rank_in_archive_order":6,"of":12,"metrics":{"H-Score":"50.8","Source-free":"yes"},"uses_additional_data":false},{"leaderboard":"/sota/universal-domain-adaptation-on-office-31","task":"Universal Domain Adaptation","dataset":"Office-31","model":"LEAD","rank_in_archive_order":6,"of":12,"metrics":{"H-score":"87.8","Source-Free":"yes"},"uses_additional_data":false},{"leaderboard":"/sota/universal-domain-adaptation-on-office-home","task":"Universal Domain Adaptation","dataset":"Office-Home","model":"LEAD","rank_in_archive_order":8,"of":14,"metrics":{"H-Score":"75.0","Source-free":"yes","VLM":"no"},"uses_additional_data":false},{"leaderboard":"/sota/universal-domain-adaptation-on-visda2017","task":"Universal Domain Adaptation","dataset":"VisDA2017","model":"LEAD","rank_in_archive_order":2,"of":13,"metrics":{"H-score":"76.6","Source-free":"yes"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.03421","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.03421"}},"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/ispc-lab/lead","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ispc-lab/glc","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":6,"ran":3,"unverified":2},"by_repo_kind":{"official":{"samples":2,"ran":1,"repositories":1},"listed":{"samples":9,"ran":8,"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":9,"samples":[{"code_sha256_prefix":"94b5622f0aa7add1","entry":"Entropy","repo":"ispc-lab/glc","repo_kind":"listed","path":"utils/net_utils.py","file_url":"https://github.com/ispc-lab/glc/blob/HEAD/utils/net_utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"94b5622f0aa7add1"}},{"code_sha256_prefix":"a7928c7cf111366a","entry":"log_args","repo":"ispc-lab/glc","repo_kind":"listed","path":"utils/net_utils.py","file_url":"https://github.com/ispc-lab/glc/blob/HEAD/utils/net_utils.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a7928c7cf111366a"}},{"code_sha256_prefix":"0b7ffc9f8b77529c","entry":"lr_scheduler","repo":"ispc-lab/glc","repo_kind":"listed","path":"train_source.py","file_url":"https://github.com/ispc-lab/glc/blob/HEAD/train_source.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0b7ffc9f8b77529c"}},{"code_sha256_prefix":"93a11f62e4a129f0","entry":"op_copy","repo":"ispc-lab/glc","repo_kind":"listed","path":"train_source.py","file_url":"https://github.com/ispc-lab/glc/blob/HEAD/train_source.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"93a11f62e4a129f0"}},{"code_sha256_prefix":"59fb5d13731e4308","entry":"set_logger","repo":"ispc-lab/glc","repo_kind":"listed","path":"utils/net_utils.py","file_url":"https://github.com/ispc-lab/glc/blob/HEAD/utils/net_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"59fb5d13731e4308"}},{"code_sha256_prefix":"218cf492f8713f71","entry":"set_logger","repo":"ispc-lab/lead","repo_kind":"official","path":"utils/net_utils.py","file_url":"https://github.com/ispc-lab/lead/blob/HEAD/utils/net_utils.py","link_basis":"first_harvest_node","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":"218cf492f8713f71"}},{"code_sha256_prefix":"13b7b1c692c187e0","entry":"test_transform","repo":"ispc-lab/glc","repo_kind":"listed","path":"dataset/dataset.py","file_url":"https://github.com/ispc-lab/glc/blob/HEAD/dataset/dataset.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"13b7b1c692c187e0"}},{"code_sha256_prefix":"e4b2648a312cebb6","entry":"train","repo":"ispc-lab/glc","repo_kind":"listed","path":"train_source.py","file_url":"https://github.com/ispc-lab/glc/blob/HEAD/train_source.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e4b2648a312cebb6"}},{"code_sha256_prefix":"ada9656c14c75934","entry":"train_transform","repo":"ispc-lab/glc","repo_kind":"listed","path":"dataset/dataset.py","file_url":"https://github.com/ispc-lab/glc/blob/HEAD/dataset/dataset.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ada9656c14c75934"}},{"code_sha256_prefix":"f64aa135fdd5f173","entry":"obtain_LEAD_pseudo_labels","repo":"ispc-lab/lead","repo_kind":"official","path":"train_target.py","file_url":"https://github.com/ispc-lab/lead/blob/HEAD/train_target.py","link_basis":"first_harvest_node","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":"f64aa135fdd5f173"}},{"code_sha256_prefix":"5b48697e26a31d82","entry":"obtain_global_pseudo_labels","repo":"ispc-lab/glc","repo_kind":"listed","path":"train_target.py","file_url":"https://github.com/ispc-lab/glc/blob/HEAD/train_target.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":"5b48697e26a31d82"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}