{"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/discriminative-feature-alignment","title":"Discriminative Feature Alignment: Improving Transferability of Unsupervised Domain Adaptation by Gaussian-guided Latent Alignment","arxiv_id":"2006.12770","date":"2020-06-23","proceeding":null,"authors":["Jing Wang","Jiahong Chen","Jianzhe Lin","Leonid Sigal","Clarence W. de Silva"],"abstract":"In this study, we focus on the unsupervised domain adaptation problem where an approximate inference model is to be learned from a labeled data domain and expected to generalize well to an unlabeled data domain. The success of unsupervised domain adaptation largely relies on the cross-domain feature alignment. Previous work has attempted to directly align latent features by the classifier-induced discrepancies. Nevertheless, a common feature space cannot always be learned via this direct feature alignment especially when a large domain gap exists. To solve this problem, we introduce a Gaussian-guided latent alignment approach to align the latent feature distributions of the two domains under the guidance of the prior distribution. In such an indirect way, the distributions over the samples from the two domains will be constructed on a common feature space, i.e., the space of the prior, which promotes better feature alignment. To effectively align the target latent distribution with this prior distribution, we also propose a novel unpaired L1-distance by taking advantage of the formulation of the encoder-decoder. The extensive evaluations on nine benchmark datasets validate the superior knowledge transferability through outperforming state-of-the-art methods and the versatility of the proposed method by improving the existing work significantly.","url_abs":"https://arxiv.org/abs/2006.12770v5","url_pdf":"https://arxiv.org/pdf/2006.12770v5.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":"discriminative-feature-alignment","repo_url":"https://github.com/JingWang18/Discriminative-Feature-Alignment","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"domain-generalization","task_name":"Domain Generalization"},{"task_slug":"traffic-sign-recognition","task_name":"Traffic Sign Recognition"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"unsupervised-domain-adaptation","task_name":"Unsupervised Domain Adaptation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/domain-adaptation-on-imageclef-da","task":"Domain Adaptation","dataset":"ImageCLEF-DA","model":"DFA-SAFN","rank_in_archive_order":5,"of":17,"metrics":{"Accuracy":"90.2"},"uses_additional_data":false},{"leaderboard":"/sota/domain-adaptation-on-imageclef-da","task":"Domain Adaptation","dataset":"ImageCLEF-DA","model":"DFA-ENT","rank_in_archive_order":7,"of":17,"metrics":{"Accuracy":"89.1"},"uses_additional_data":false},{"leaderboard":"/sota/domain-adaptation-on-mnist-to-usps","task":"Domain Adaptation","dataset":"MNIST-to-USPS","model":"DFA-MCD","rank_in_archive_order":3,"of":14,"metrics":{"Accuracy":"98.6"},"uses_additional_data":false},{"leaderboard":"/sota/domain-adaptation-on-mnist-to-usps","task":"Domain Adaptation","dataset":"MNIST-to-USPS","model":"DFA-ENT","rank_in_archive_order":7,"of":14,"metrics":{"Accuracy":"97.9"},"uses_additional_data":false},{"leaderboard":"/sota/domain-adaptation-on-svhn-to-mnist","task":"Domain Adaptation","dataset":"SVHN-to-MNIST","model":"DFA-MCD","rank_in_archive_order":3,"of":14,"metrics":{"Accuracy":"98.9"},"uses_additional_data":false},{"leaderboard":"/sota/domain-adaptation-on-svhn-to-mnist","task":"Domain Adaptation","dataset":"SVHN-to-MNIST","model":"DFA-ENT","rank_in_archive_order":5,"of":14,"metrics":{"Accuracy":"98.2"},"uses_additional_data":false},{"leaderboard":"/sota/domain-adaptation-on-synsig-to-gtsrb","task":"Domain Adaptation","dataset":"SYNSIG-to-GTSRB","model":"DFA-MCD","rank_in_archive_order":1,"of":6,"metrics":{"Accuracy":"97.5"},"uses_additional_data":false},{"leaderboard":"/sota/domain-adaptation-on-synsig-to-gtsrb","task":"Domain Adaptation","dataset":"SYNSIG-to-GTSRB","model":"DFA-ENT","rank_in_archive_order":2,"of":6,"metrics":{"Accuracy":"96.8"},"uses_additional_data":false},{"leaderboard":"/sota/domain-adaptation-on-usps-to-mnist","task":"Domain Adaptation","dataset":"USPS-to-MNIST","model":"DFA-MCD","rank_in_archive_order":9,"of":14,"metrics":{"Accuracy":"96.6"},"uses_additional_data":false},{"leaderboard":"/sota/domain-adaptation-on-usps-to-mnist","task":"Domain Adaptation","dataset":"USPS-to-MNIST","model":"DFA-ENT","rank_in_archive_order":12,"of":14,"metrics":{"Accuracy":"96.2"},"uses_additional_data":false},{"leaderboard":"/sota/transfer-learning-on-office-home","task":"Transfer Learning","dataset":"Office-Home","model":"DFA-ENT","rank_in_archive_order":2,"of":5,"metrics":{"Accuracy":"69.2"},"uses_additional_data":false},{"leaderboard":"/sota/transfer-learning-on-office-home","task":"Transfer Learning","dataset":"Office-Home","model":"DFA-SAFN","rank_in_archive_order":3,"of":5,"metrics":{"Accuracy":"69.1"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2006.12770","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.12770"}},"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/JingWang18/Discriminative-Feature-Alignment","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"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":"9546e8417b4bdc1a","entry":"grad_reverse","repo":"JingWang18/Discriminative-Feature-Alignment","repo_kind":"official","path":"Digit_Classification/DFAENT/model/grad_reverse.py","file_url":"https://github.com/JingWang18/Discriminative-Feature-Alignment/blob/HEAD/Digit_Classification/DFAENT/model/grad_reverse.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":"9546e8417b4bdc1a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}