{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/learning-metrics-from-teachers-compact","title":"Learning Metrics from Teachers: Compact Networks for Image Embedding","arxiv_id":"1904.03624","date":"2019-04-07","proceeding":"CVPR 2019 6","authors":["Lu Yu","Vacit Oguz Yazici","Xialei Liu","Joost Van de Weijer","Yongmei Cheng","Arnau Ramisa"],"abstract":"Metric learning networks are used to compute image embeddings, which are\nwidely used in many applications such as image retrieval and face recognition.\nIn this paper, we propose to use network distillation to efficiently compute\nimage embeddings with small networks. Network distillation has been\nsuccessfully applied to improve image classification, but has hardly been\nexplored for metric learning. To do so, we propose two new loss functions that\nmodel the communication of a deep teacher network to a small student network.\nWe evaluate our system in several datasets, including CUB-200-2011, Cars-196,\nStanford Online Products and show that embeddings computed using small student\nnetworks perform significantly better than those computed using standard\nnetworks of similar size. Results on a very compact network (MobileNet-0.25),\nwhich can be used on mobile devices, show that the proposed method can greatly\nimprove Recall@1 results from 27.5\\% to 44.6\\%. Furthermore, we investigate\nvarious aspects of distillation for embeddings, including hint and attention\nlayers, semi-supervised learning and cross quality distillation. (Code is\navailable at https://github.com/yulu0724/EmbeddingDistillation.)","url_abs":"http://arxiv.org/abs/1904.03624v1","url_pdf":"http://arxiv.org/pdf/1904.03624v1.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":"learning-metrics-from-teachers-compact","repo_url":"https://github.com/yulu0724/EmbeddingDistillation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"face-recognition","task_name":"Face Recognition"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"metric-learning","task_name":"Metric Learning"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1904.03624","atlas_url":"https://app.syntology.ai/?focus=1904.03624","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1904.03624"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1904.03624\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1904.03624"},"call":"get_concepts_for_paper(arxiv_id=\"1904.03624\")"}],"by_repo":[{"repo":"yulu0724/EmbeddingDistillation","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"aa31b2b01a628f409a169bf6da155ee9560c1e7854b67434a4f5725c0fda1617","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}