{"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/proxy-anchor-loss-for-deep-metric-learning","title":"Proxy Anchor Loss for Deep Metric Learning","arxiv_id":"2003.13911","date":"2020-03-31","proceeding":"CVPR 2020 6","authors":["Sungyeon Kim","Dongwon Kim","Minsu Cho","Suha Kwak"],"abstract":"Existing metric learning losses can be categorized into two classes: pair-based and proxy-based losses. The former class can leverage fine-grained semantic relations between data points, but slows convergence in general due to its high training complexity. In contrast, the latter class enables fast and reliable convergence, but cannot consider the rich data-to-data relations. This paper presents a new proxy-based loss that takes advantages of both pair- and proxy-based methods and overcomes their limitations. Thanks to the use of proxies, our loss boosts the speed of convergence and is robust against noisy labels and outliers. At the same time, it allows embedding vectors of data to interact with each other in its gradients to exploit data-to-data relations. Our method is evaluated on four public benchmarks, where a standard network trained with our loss achieves state-of-the-art performance and most quickly converges.","url_abs":"https://arxiv.org/abs/2003.13911v1","url_pdf":"https://arxiv.org/pdf/2003.13911v1.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":"proxy-anchor-loss-for-deep-metric-learning","repo_url":"https://github.com/tjddus9597/Proxy-Anchor-CVPR2020","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"proxy-anchor-loss-for-deep-metric-learning","repo_url":"https://github.com/QuocThangNguyen/deep-metric-learning-tsinghua-dogs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"proxy-anchor-loss-for-deep-metric-learning","repo_url":"https://github.com/zhen8838/Circle-Loss","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"fine-grained-image-classification","task_name":"Fine-Grained Image Classification"},{"task_slug":"fine-grained-vehicle-classification","task_name":"Fine-Grained Vehicle Classification"},{"task_slug":"metric-learning","task_name":"Metric Learning"}],"methods":[{"method_slug":"proxyanchorloss","method_name":"ProxyAnchorLoss"},{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[{"slug":"proxyanchorloss","name":"ProxyAnchorLoss","full_name":"Proxy Anchor Loss for Deep Metric Learning"}],"results":[{"leaderboard":"/sota/metric-learning-on-cars196","task":"Metric Learning","dataset":"CARS196","model":"BN-Inception + Proxy-Anchor","rank_in_archive_order":16,"of":36,"metrics":{"R@1":"88.3"},"uses_additional_data":true},{"leaderboard":"/sota/metric-learning-on-cub-200-2011","task":"Metric Learning","dataset":"CUB-200-2011","model":"BN-Inception + Proxy-Anchor","rank_in_archive_order":10,"of":30,"metrics":{"R@1":"71.1"},"uses_additional_data":true},{"leaderboard":"/sota/metric-learning-on-stanford-online-products-1","task":"Metric Learning","dataset":"Stanford Online Products","model":"BN-Inception + Proxy-Anchor","rank_in_archive_order":24,"of":33,"metrics":{"R@1":"80.3"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2003.13911","atlas_url":"https://app.syntology.ai/?focus=2003.13911","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":"2003.13911"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2003.13911\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2003.13911"},"call":"get_concepts_for_paper(arxiv_id=\"2003.13911\")"}],"by_repo":[{"repo":"tjddus9597/Proxy-Anchor-CVPR2020","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"QuocThangNguyen/deep-metric-learning-tsinghua-dogs","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":2,"harvested_for":["1503.03832","1909.05235"],"harvested_for_calls":[{"arxiv_id":"1503.03832","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1503.03832"},"call":"get_harvested_code_for_paper(arxiv_id=\"1503.03832\")"},{"arxiv_id":"1909.05235","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1909.05235"},"call":"get_harvested_code_for_paper(arxiv_id=\"1909.05235\")"}]},{"repo":"zhen8838/Circle-Loss","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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":"ae3f5793e36ca77e90e1aa409b11068bd7fd2f0e62926cf3a10b9e1974ca73eb","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}