{"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/deep-metric-learning-beyond-binary","title":"Deep Metric Learning Beyond Binary Supervision","arxiv_id":"1904.09626","date":"2019-04-21","proceeding":"CVPR 2019 6","authors":["Sungyeon Kim","Minkyo Seo","Ivan Laptev","Minsu Cho","Suha Kwak"],"abstract":"Metric Learning for visual similarity has mostly adopted binary supervision\nindicating whether a pair of images are of the same class or not. Such a binary\nindicator covers only a limited subset of image relations, and is not\nsufficient to represent semantic similarity between images described by\ncontinuous and/or structured labels such as object poses, image captions, and\nscene graphs. Motivated by this, we present a novel method for deep metric\nlearning using continuous labels. First, we propose a new triplet loss that\nallows distance ratios in the label space to be preserved in the learned metric\nspace. The proposed loss thus enables our model to learn the degree of\nsimilarity rather than just the order. Furthermore, we design a triplet mining\nstrategy adapted to metric learning with continuous labels. We address three\ndifferent image retrieval tasks with continuous labels in terms of human poses,\nroom layouts and image captions, and demonstrate the superior performance of\nour approach compared to previous methods.","url_abs":"http://arxiv.org/abs/1904.09626v1","url_pdf":"http://arxiv.org/pdf/1904.09626v1.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":"deep-metric-learning-beyond-binary","repo_url":"https://github.com/tjddus9597/Beyond-Binary-Supervision-CVPR19","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}}],"tasks":[{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"metric-learning","task_name":"Metric Learning"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"semantic-similarity","task_name":"Semantic Similarity"},{"task_slug":"semantic-textual-similarity","task_name":"Semantic Textual Similarity"},{"task_slug":null,"task_name":"Triplet"}],"methods":[{"method_slug":"triplet-loss","method_name":"Triplet Loss"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.09626","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}