{"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/learning-transferable-features-with-deep","title":"Learning Transferable Features with Deep Adaptation Networks","arxiv_id":"1502.02791","date":"2015-02-10","proceeding":null,"authors":["Mingsheng Long","Yue Cao","Jian-Min Wang","Michael. I. Jordan"],"abstract":"Recent studies reveal that a deep neural network can learn transferable\nfeatures which generalize well to novel tasks for domain adaptation. However,\nas deep features eventually transition from general to specific along the\nnetwork, the feature transferability drops significantly in higher layers with\nincreasing domain discrepancy. Hence, it is important to formally reduce the\ndataset bias and enhance the transferability in task-specific layers. In this\npaper, we propose a new Deep Adaptation Network (DAN) architecture, which\ngeneralizes deep convolutional neural network to the domain adaptation\nscenario. In DAN, hidden representations of all task-specific layers are\nembedded in a reproducing kernel Hilbert space where the mean embeddings of\ndifferent domain distributions can be explicitly matched. The domain\ndiscrepancy is further reduced using an optimal multi-kernel selection method\nfor mean embedding matching. DAN can learn transferable features with\nstatistical guarantees, and can scale linearly by unbiased estimate of kernel\nembedding. Extensive empirical evidence shows that the proposed architecture\nyields state-of-the-art image classification error rates on standard domain\nadaptation benchmarks.","url_abs":"http://arxiv.org/abs/1502.02791v2","url_pdf":"http://arxiv.org/pdf/1502.02791v2.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":"learning-transferable-features-with-deep","repo_url":"https://github.com/JorisRoels/domain-adaptive-segmentation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"learning-transferable-features-with-deep","repo_url":"https://github.com/thuml/Transfer-Learning-Library","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"learning-transferable-features-with-deep","repo_url":"https://github.com/CtrlZ1/Domain-Adaptation-Algorithms","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"learning-transferable-features-with-deep","repo_url":"https://github.com/CtrlZ1/Domain-Adaptive-CodeBase","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"learning-transferable-features-with-deep","repo_url":"https://github.com/kevinmusgrave/pytorch-adapt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"multi-source-unsupervised-domain-adaptation","task_name":"Multi-Source Unsupervised Domain Adaptation"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/domain-adaptation-on-imageclef-da","task":"Domain Adaptation","dataset":"ImageCLEF-DA","model":"DAN","rank_in_archive_order":17,"of":17,"metrics":{"Accuracy":"76.9"},"uses_additional_data":false},{"leaderboard":"/sota/domain-adaptation-on-mnist-to-mnist-m","task":"Domain Adaptation","dataset":"MNIST-to-MNIST-M","model":"MMD [tzeng2015ddc]; [long2015learning]","rank_in_archive_order":5,"of":5,"metrics":{"Accuracy":"76.9"},"uses_additional_data":false},{"leaderboard":"/sota/domain-adaptation-on-office-caltech","task":"Domain Adaptation","dataset":"Office-Caltech","model":"DAN[[Long et al.2015]]","rank_in_archive_order":4,"of":8,"metrics":{"Average Accuracy":"90.1"},"uses_additional_data":false},{"leaderboard":"/sota/domain-adaptation-on-svnh-to-mnist","task":"Domain Adaptation","dataset":"SVNH-to-MNIST","model":"MMD [tzeng2015ddc]; [long2015learning]","rank_in_archive_order":8,"of":9,"metrics":{"Accuracy":"71.1"},"uses_additional_data":false},{"leaderboard":"/sota/domain-adaptation-on-synsig-to-gtsrb","task":"Domain Adaptation","dataset":"SYNSIG-to-GTSRB","model":"DAN","rank_in_archive_order":5,"of":6,"metrics":{"Accuracy":"91.1"},"uses_additional_data":false},{"leaderboard":"/sota/domain-adaptation-on-synth-digits-to-svhn","task":"Domain Adaptation","dataset":"Synth Digits-to-SVHN","model":"MMD [tzeng2015ddc]; [long2015learning]","rank_in_archive_order":3,"of":4,"metrics":{"Accuracy":"88.0"},"uses_additional_data":false},{"leaderboard":"/sota/domain-adaptation-on-synth-signs-to-gtsrb","task":"Domain Adaptation","dataset":"Synth Signs-to-GTSRB","model":"MMD [tzeng2015ddc]; [long2015learning]","rank_in_archive_order":3,"of":4,"metrics":{"Accuracy":"91.1"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-domain-adaptation-on-office-home","task":"Unsupervised Domain Adaptation","dataset":"Office-Home","model":"DAN [cite:ICML15DAN]","rank_in_archive_order":15,"of":20,"metrics":{"Accuracy":"74.3"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1502.02791","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1502.02791"}},"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/kevinmusgrave/pytorch-adapt","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/thuml/Transfer-Learning-Library","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/CtrlZ1/Domain-Adaptation-Algorithms","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/CtrlZ1/Domain-Adaptive-CodeBase","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/JorisRoels/domain-adaptive-segmentation","reach":null}],"summary":{"ran":1,"ran_honours":1},"by_repo_kind":{"listed":{"samples":2,"ran":2,"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":"1708f6b9ceb54667","entry":"MultipleKernelMaximumMeanDiscrepancy","repo":"thuml/Transfer-Learning-Library","repo_kind":"listed","path":"tllib/alignment/dan.py","file_url":"https://github.com/thuml/Transfer-Learning-Library/blob/HEAD/tllib/alignment/dan.py","link_basis":"first_harvest_node","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":"1708f6b9ceb54667"}},{"code_sha256_prefix":"33d1fd5324280e24","entry":"_update_index_matrix","repo":"thuml/Transfer-Learning-Library","repo_kind":"listed","path":"tllib/alignment/dan.py","file_url":"https://github.com/thuml/Transfer-Learning-Library/blob/HEAD/tllib/alignment/dan.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"33d1fd5324280e24"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}