{"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/generalization-in-metric-learning-should-the","title":"Generalization in Metric Learning: Should the Embedding Layer be the Embedding Layer?","arxiv_id":"1803.03310","date":"2018-03-08","proceeding":null,"authors":["Nam Vo","James Hays"],"abstract":"This work studies deep metric learning under small to medium scale data as we\nbelieve that better generalization could be a contributing factor to the\nimprovement of previous fine-grained image retrieval methods; it should be\nconsidered when designing future techniques. In particular, we investigate\nusing other layers in a deep metric learning system (besides the embedding\nlayer) for feature extraction and analyze how well they perform on training\ndata and generalize to testing data. From this study, we suggest a new\nregularization practice where one can add or choose a more optimal layer for\nfeature extraction. State-of-the-art performance is demonstrated on 3\nfine-grained image retrieval benchmarks: Cars-196, CUB-200-2011, and Stanford\nOnline Product.","url_abs":"http://arxiv.org/abs/1803.03310v2","url_pdf":"http://arxiv.org/pdf/1803.03310v2.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":"generalization-in-metric-learning-should-the","repo_url":"https://github.com/lugiavn/generalization-dml","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"metric-learning","task_name":"Metric Learning"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}