{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/domain-consensus-clustering-for-universal","title":"Domain Consensus Clustering for Universal Domain Adaptation","arxiv_id":null,"date":"2021-06-05","proceeding":"CVPR 2021 1","authors":["Guangrui Li","Guoliang Kang","Yi Zhu","Yunchao Wei","Yi Yang"],"abstract":"In this paper, we investigate Universal Domain Adaptation (UniDA) problem, which aims to transfer the knowledge from source to target under unaligned label space. The main challenge of UniDA lies in how to separate common classes (i.e., classes shared across domains), from private classes (i.e., classes only exist in one domain). Previous works treat the private samples in the target as one generic class but ignore their intrinsic structure. Consequently, the resulting representations are not compact enough in the latent space and can be easily confused with common samples. To better exploit the intrinsic structure of the target domain, we propose Domain Consensus Clustering (DCC), which exploits the domain consensus knowledge to discover discriminative clusters on both common samples and private ones. Specifically, we draw the domain consensus knowledge from two aspects to facilitate the clustering and the private class discovery, i.e., the semantic-level consensus, which identifies the cycle-consistent clusters as the common classes, and the sample-level consensus, which utilizes the cross-domain classification agreement to determine the number of clusters and discover the private classes. Based on DCC, we are able to separate the private classes from the common ones, and differentiate the private classes themselves. Finally, we apply a class-aware alignment technique on identified common samples to minimize the distribution shift, and a prototypical regularizer to inspire discriminative target clusters. \r\nExperiments on four benchmarks demonstrate DCC significantly outperforms previous state-of-the-arts.","url_abs":"http://www.guangrui.li/papers/guangruiCVPR2021.pdf","url_pdf":"http://www.guangrui.li/papers/guangruiCVPR2021.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":"domain-consensus-clustering-for-universal","repo_url":"https://github.com/Solacex/Domain-Consensus-Clustering","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"open-set-learning","task_name":"Open Set Learning"},{"task_slug":"partial-domain-adaptation","task_name":"Partial Domain Adaptation"},{"task_slug":"universal-domain-adaptation","task_name":"Universal Domain Adaptation"},{"task_slug":"domain-classification","task_name":"domain classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/partial-domain-adaptation-on-office-31","task":"Partial Domain Adaptation","dataset":"Office-31","model":"DCC","rank_in_archive_order":4,"of":7,"metrics":{"Accuracy (%)":"97.90"},"uses_additional_data":false},{"leaderboard":"/sota/universal-domain-adaptation-on-domainnet","task":"Universal Domain Adaptation","dataset":"DomainNet","model":"DCC","rank_in_archive_order":8,"of":12,"metrics":{"H-Score":"49.20","Source-free":"no"},"uses_additional_data":false},{"leaderboard":"/sota/universal-domain-adaptation-on-office-31","task":"Universal Domain Adaptation","dataset":"Office-31","model":"DCC","rank_in_archive_order":10,"of":12,"metrics":{"H-score":"80.16","Source-Free":"no"},"uses_additional_data":false},{"leaderboard":"/sota/universal-domain-adaptation-on-office-home","task":"Universal Domain Adaptation","dataset":"Office-Home","model":"DCC","rank_in_archive_order":10,"of":14,"metrics":{"H-Score":"70.18","Source-free":"no","VLM":"no"},"uses_additional_data":false},{"leaderboard":"/sota/universal-domain-adaptation-on-visda2017","task":"Universal Domain Adaptation","dataset":"VisDA2017","model":"DCC","rank_in_archive_order":12,"of":13,"metrics":{"H-score":"43.0","Source-free":"no"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"no_arxiv_id","checked_against":null,"by_repo":[{"repo":"Solacex/Domain-Consensus-Clustering","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2206.07551"],"harvested_for_calls":[{"arxiv_id":"2206.07551","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2206.07551"},"call":"get_harvested_code_for_paper(arxiv_id=\"2206.07551\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"17a1ddb14f4b563b6d6b499e7057c6ff4da6f427f3752cb5726fe3d19b82a8de","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}