{"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/unsupervised-visual-domain-adaptation-a-deep","title":"Unsupervised Visual Domain Adaptation: A Deep Max-Margin Gaussian Process Approach","arxiv_id":"1902.08727","date":"2019-02-23","proceeding":"CVPR 2019 6","authors":["Minyoung Kim","Pritish Sahu","Behnam Gholami","Vladimir Pavlovic"],"abstract":"In unsupervised domain adaptation, it is widely known that the target domain\nerror can be provably reduced by having a shared input representation that\nmakes the source and target domains indistinguishable from each other. Very\nrecently it has been studied that not just matching the marginal input\ndistributions, but the alignment of output (class) distributions is also\ncritical. The latter can be achieved by minimizing the maximum discrepancy of\npredictors (classifiers). In this paper, we adopt this principle, but propose a\nmore systematic and effective way to achieve hypothesis consistency via\nGaussian processes (GP). The GP allows us to define/induce a hypothesis space\nof the classifiers from the posterior distribution of the latent random\nfunctions, turning the learning into a simple large-margin posterior separation\nproblem, far easier to solve than previous approaches based on adversarial\nminimax optimization. We formulate a learning objective that effectively pushes\nthe posterior to minimize the maximum discrepancy. This is further shown to be\nequivalent to maximizing margins and minimizing uncertainty of the class\npredictions in the target domain, a well-established principle in classical\n(semi-)supervised learning. Empirical results demonstrate that our approach is\ncomparable or superior to the existing methods on several benchmark domain\nadaptation datasets.","url_abs":"http://arxiv.org/abs/1902.08727v1","url_pdf":"http://arxiv.org/pdf/1902.08727v1.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":"unsupervised-visual-domain-adaptation-a-deep","repo_url":"https://github.com/seqam-lab/GPDA","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":"gaussian-processes","task_name":"Gaussian Processes"},{"task_slug":"unsupervised-domain-adaptation","task_name":"Unsupervised Domain Adaptation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/synthetic-to-real-translation-on-syn2real-c","task":"Synthetic-to-Real Translation","dataset":"Syn2Real-C","model":"GPDA","rank_in_archive_order":3,"of":6,"metrics":{"Accuracy":"73.3"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1902.08727","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.08727"}},"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/seqam-lab/GPDA","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":2},"by_repo_kind":{"listed":{"samples":2,"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":"d56d4b8cd4578725","entry":"convert_label_10_to_0","repo":"seqam-lab/GPDA","repo_kind":"listed","path":"src/utils/utils.py","file_url":"https://github.com/seqam-lab/GPDA/blob/HEAD/src/utils/utils.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":"d56d4b8cd4578725"}},{"code_sha256_prefix":"c3e19a4b614256b8","entry":"load_mnist","repo":"seqam-lab/GPDA","repo_kind":"listed","path":"src/data_manager/mnist.py","file_url":"https://github.com/seqam-lab/GPDA/blob/HEAD/src/data_manager/mnist.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":"c3e19a4b614256b8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}