{"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/class-overwhelms-mutual-conditional-blended","title":"Class Overwhelms: Mutual Conditional Blended-Target Domain Adaptation","arxiv_id":"2302.01516","date":"2023-02-03","proceeding":null,"authors":["Pengcheng Xu","Boyu Wang","Charles Ling"],"abstract":"Current methods of blended targets domain adaptation (BTDA) usually infer or consider domain label information but underemphasize hybrid categorical feature structures of targets, which yields limited performance, especially under the label distribution shift. We demonstrate that domain labels are not directly necessary for BTDA if categorical distributions of various domains are sufficiently aligned even facing the imbalance of domains and the label distribution shift of classes. However, we observe that the cluster assumption in BTDA does not comprehensively hold. The hybrid categorical feature space hinders the modeling of categorical distributions and the generation of reliable pseudo labels for categorical alignment. To address these, we propose a categorical domain discriminator guided by uncertainty to explicitly model and directly align categorical distributions $P(Z|Y)$. Simultaneously, we utilize the low-level features to augment the single source features with diverse target styles to rectify the biased classifier $P(Y|Z)$ among diverse targets. Such a mutual conditional alignment of $P(Z|Y)$ and $P(Y|Z)$ forms a mutual reinforced mechanism. Our approach outperforms the state-of-the-art in BTDA even compared with methods utilizing domain labels, especially under the label distribution shift, and in single target DA on DomainNet. Source codes are available at \\url{https://github.com/Pengchengpcx/Class-overwhelms-Mutual-Conditional-Blended-Target-Domain-Adaptation}.","url_abs":"https://arxiv.org/abs/2302.01516v2","url_pdf":"https://arxiv.org/pdf/2302.01516v2.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":"class-overwhelms-mutual-conditional-blended","repo_url":"https://github.com/Pengchengpcx/Class-overwhelms-Mutual-Conditional-Blended-Target-Domain-Adaptation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"blended-target-domain-adaptation","task_name":"Blended-target Domain Adaptation"},{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"label-shift-of-blended-target-domain","task_name":"Label shift of blended-target domain adaptation"},{"task_slug":"multi-target-domain-adaptation","task_name":"Multi-target Domain Adaptation"}],"methods":[{"method_slug":"align","method_name":"ALIGN"}],"datasets_introduced":[{"slug":"office-home-lmt","name":"Office-Home-LMT","full_name":"Imbalance datasets for multi-domain adaptation"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/blended-target-domain-adaptation-on-domainnet","task":"Blended-target Domain Adaptation","dataset":"DomainNet","model":"MCDA","rank_in_archive_order":1,"of":2,"metrics":{"Average Accuracy":"34.5"},"uses_additional_data":false},{"leaderboard":"/sota/blended-target-domain-adaptation-on-office-31","task":"Blended-target Domain Adaptation","dataset":"Office-31","model":"MCDA","rank_in_archive_order":1,"of":2,"metrics":{"Average Accuracy":"89.6"},"uses_additional_data":false},{"leaderboard":"/sota/blended-target-domain-adaptation-on-office","task":"Blended-target Domain Adaptation","dataset":"Office-Home","model":"MCDA","rank_in_archive_order":1,"of":2,"metrics":{"Average Accuracy":"71.1"},"uses_additional_data":false},{"leaderboard":"/sota/multi-target-domain-adaptation-on-domainnet","task":"Multi-target Domain Adaptation","dataset":"DomainNet","model":"MCDA","rank_in_archive_order":1,"of":4,"metrics":{"Accuracy":"34.5"},"uses_additional_data":false},{"leaderboard":"/sota/multi-target-domain-adaptation-on-office-31","task":"Multi-target Domain Adaptation","dataset":"Office-31","model":"MCDA","rank_in_archive_order":1,"of":5,"metrics":{"Accuracy":"89.6"},"uses_additional_data":false},{"leaderboard":"/sota/multi-target-domain-adaptation-on-office-home","task":"Multi-target Domain Adaptation","dataset":"Office-Home","model":"MCDA","rank_in_archive_order":1,"of":4,"metrics":{"Accuracy":"71.1"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2302.01516","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.01516"}},"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/Pengchengpcx/Class-overwhelms-Mutual-Conditional-Blended-Target-Domain-Adaptation","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"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":"4d3faaaa1c706b0b","entry":"accuracy","repo":"Pengchengpcx/Class-overwhelms-Mutual-Conditional-Blended-Target-Domain-Adaptation","repo_kind":"official","path":"util.py","file_url":"https://github.com/Pengchengpcx/Class-overwhelms-Mutual-Conditional-Blended-Target-Domain-Adaptation/blob/HEAD/util.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":"4d3faaaa1c706b0b"}},{"code_sha256_prefix":"96d1a27e3ffdf6f9","entry":"cal_acc","repo":"Pengchengpcx/Class-overwhelms-Mutual-Conditional-Blended-Target-Domain-Adaptation","repo_kind":"official","path":"models/evaluation.py","file_url":"https://github.com/Pengchengpcx/Class-overwhelms-Mutual-Conditional-Blended-Target-Domain-Adaptation/blob/HEAD/models/evaluation.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":"96d1a27e3ffdf6f9"}},{"code_sha256_prefix":"8193561fbc0c0bdd","entry":"confidence_pseudo_label","repo":"Pengchengpcx/Class-overwhelms-Mutual-Conditional-Blended-Target-Domain-Adaptation","repo_kind":"official","path":"util.py","file_url":"https://github.com/Pengchengpcx/Class-overwhelms-Mutual-Conditional-Blended-Target-Domain-Adaptation/blob/HEAD/util.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":"8193561fbc0c0bdd"}},{"code_sha256_prefix":"a5905023bd0121fc","entry":"load_model","repo":"Pengchengpcx/Class-overwhelms-Mutual-Conditional-Blended-Target-Domain-Adaptation","repo_kind":"official","path":"util.py","file_url":"https://github.com/Pengchengpcx/Class-overwhelms-Mutual-Conditional-Blended-Target-Domain-Adaptation/blob/HEAD/util.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":"a5905023bd0121fc"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}