{"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/repmet-representative-based-metric-learning","title":"RepMet: Representative-based metric learning for classification and one-shot object detection","arxiv_id":"1806.04728","date":"2018-06-12","proceeding":null,"authors":["Leonid Karlinsky","Joseph Shtok","Sivan Harary","Eli Schwartz","Amit Aides","Rogerio Feris","Raja Giryes","Alex M. Bronstein"],"abstract":"Distance metric learning (DML) has been successfully applied to object\nclassification, both in the standard regime of rich training data and in the\nfew-shot scenario, where each category is represented by only a few examples.\nIn this work, we propose a new method for DML that simultaneously learns the\nbackbone network parameters, the embedding space, and the multi-modal\ndistribution of each of the training categories in that space, in a single\nend-to-end training process. Our approach outperforms state-of-the-art methods\nfor DML-based object classification on a variety of standard fine-grained\ndatasets. Furthermore, we demonstrate the effectiveness of our approach on the\nproblem of few-shot object detection, by incorporating the proposed DML\narchitecture as a classification head into a standard object detection model.\nWe achieve the best results on the ImageNet-LOC dataset compared to strong\nbaselines, when only a few training examples are available. We also offer the\ncommunity a new episodic benchmark based on the ImageNet dataset for the\nfew-shot object detection task.","url_abs":"http://arxiv.org/abs/1806.04728v3","url_pdf":"http://arxiv.org/pdf/1806.04728v3.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":"repmet-representative-based-metric-learning","repo_url":"https://github.com/jshtok/RepMet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mxnet","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"few-shot-object-detection","task_name":"Few-Shot Object Detection"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"metric-learning","task_name":"Metric Learning"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"one-shot-object-detection","task_name":"One-Shot Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1806.04728","atlas_url":"https://app.syntology.ai/?focus=1806.04728","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.04728"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/jshtok/RepMet","reach":null}],"summary":{"ran_honours":1},"by_repo_kind":{"listed":{"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":0,"samples":[{"code_sha256_prefix":"1f8d2cb74d49770a","entry":"bb_overlap","repo":"jshtok/RepMet","repo_kind":"listed","path":"fpn/few_shot_benchmark.py","file_url":"https://github.com/jshtok/RepMet/blob/HEAD/fpn/few_shot_benchmark.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1f8d2cb74d49770a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}