{"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/m-adda-unsupervised-domain-adaptation-with","title":"M-ADDA: Unsupervised Domain Adaptation with Deep Metric Learning","arxiv_id":"1807.02552","date":"2018-07-06","proceeding":null,"authors":["Issam Laradji","Reza Babanezhad"],"abstract":"Unsupervised domain adaptation techniques have been successful for a wide\nrange of problems where supervised labels are limited. The task is to classify\nan unlabeled `target' dataset by leveraging a labeled `source' dataset that\ncomes from a slightly similar distribution. We propose metric-based adversarial\ndiscriminative domain adaptation (M-ADDA) which performs two main steps. First,\nit uses a metric learning approach to train the source model on the source\ndataset by optimizing the triplet loss function. This results in clusters where\nembeddings of the same label are close to each other and those with different\nlabels are far from one another. Next, it uses the adversarial approach (as\nthat used in ADDA \\cite{2017arXiv170205464T}) to make the extracted features\nfrom the source and target datasets indistinguishable. Simultaneously, we\noptimize a novel loss function that encourages the target dataset's embeddings\nto form clusters. While ADDA and M-ADDA use similar architectures, we show that\nM-ADDA performs significantly better on the digits adaptation datasets of MNIST\nand USPS. This suggests that using metric-learning for domain adaptation can\nlead to large improvements in classification accuracy for the domain adaptation\ntask. The code is available at \\url{https://github.com/IssamLaradji/M-ADDA}.","url_abs":"http://arxiv.org/abs/1807.02552v1","url_pdf":"http://arxiv.org/pdf/1807.02552v1.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":"m-adda-unsupervised-domain-adaptation-with","repo_url":"https://github.com/IssamLaradji/M-ADDA","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"metric-learning","task_name":"Metric Learning"},{"task_slug":null,"task_name":"Triplet"},{"task_slug":"unsupervised-domain-adaptation","task_name":"Unsupervised Domain Adaptation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1807.02552","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.02552"}},"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/IssamLaradji/M-ADDA","reach":null}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"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":1,"samples":[{"code_sha256_prefix":"c392ab2b9beb7826","entry":"get_experiment_dict","repo":"IssamLaradji/M-ADDA","repo_kind":"official","path":"experiments.py","file_url":"https://github.com/IssamLaradji/M-ADDA/blob/HEAD/experiments.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c392ab2b9beb7826"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}