{"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/partial-fc-training-10-million-identities-on","title":"Partial FC: Training 10 Million Identities on a Single Machine","arxiv_id":"2010.05222","date":"2020-10-11","proceeding":null,"authors":["Xiang An","Xuhan Zhu","Yang Xiao","Lan Wu","Ming Zhang","Yuan Gao","Bin Qin","Debing Zhang","Ying Fu"],"abstract":"Face recognition has been an active and vital topic among computer vision community for a long time. Previous researches mainly focus on loss functions used for facial feature extraction network, among which the improvements of softmax-based loss functions greatly promote the performance of face recognition. However, the contradiction between the drastically increasing number of face identities and the shortage of GPU memories is gradually becoming irreconcilable. In this paper, we thoroughly analyze the optimization goal of softmax-based loss functions and the difficulty of training massive identities. We find that the importance of negative classes in softmax function in face representation learning is not as high as we previously thought. The experiment demonstrates no loss of accuracy when training with only 10\\% randomly sampled classes for the softmax-based loss functions, compared with training with full classes using state-of-the-art models on mainstream benchmarks. We also implement a very efficient distributed sampling algorithm, taking into account model accuracy and training efficiency, which uses only eight NVIDIA RTX2080Ti to complete classification tasks with tens of millions of identities. The code of this paper has been made available https://github.com/deepinsight/insightface/tree/master/recognition/partial_fc.","url_abs":"https://arxiv.org/abs/2010.05222v2","url_pdf":"https://arxiv.org/pdf/2010.05222v2.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":"partial-fc-training-10-million-identities-on","repo_url":"https://github.com/deepinsight/insightface","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"partial-fc-training-10-million-identities-on","repo_url":"https://github.com/deepinsight/insightface/tree/master/recognition/partial_fc","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mxnet","reach":null},{"paper_slug":"partial-fc-training-10-million-identities-on","repo_url":"https://github.com/PaddlePaddle/PLSC","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"paddle","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"partial-fc-training-10-million-identities-on","repo_url":"https://github.com/tamerthamoqa/facenet-pytorch-glint360k","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"partial-fc-training-10-million-identities-on","repo_url":"https://github.com/CoinCheung/pytorch-loss","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"partial-fc-training-10-million-identities-on","repo_url":"https://github.com/JDAI-CV/fast-reid","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"partial-fc-training-10-million-identities-on","repo_url":"https://github.com/Recognito-Vision/Android-FaceRecognition-FaceLivenessDetection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"face-identification","task_name":"Face Identification"},{"task_slug":"face-recognition","task_name":"Face Recognition"},{"task_slug":"face-verification","task_name":"Face Verification"},{"task_slug":null,"task_name":"GPU"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[{"method_slug":"arcface","method_name":"ArcFace"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[{"slug":"glint360k","name":"Glint360K","full_name":"Glint360K"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/face-identification-on-megaface","task":"Face Identification","dataset":"MegaFace","model":"PartialFC + Glint360K + R100","rank_in_archive_order":2,"of":13,"metrics":{"Accuracy":"99.10%"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2010.05222","atlas_url":"https://app.syntology.ai/?focus=2010.05222","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":"2010.05222"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2010.05222\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2010.05222"},"call":"get_concepts_for_paper(arxiv_id=\"2010.05222\")"}],"by_repo":[{"repo":"deepinsight/insightface","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2601.07576"],"harvested_for_calls":[{"arxiv_id":"2601.07576","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2601.07576"},"call":"get_harvested_code_for_paper(arxiv_id=\"2601.07576\")"}]},{"repo":"PaddlePaddle/PLSC","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2210.09461"],"harvested_for_calls":[{"arxiv_id":"2210.09461","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2210.09461"},"call":"get_harvested_code_for_paper(arxiv_id=\"2210.09461\")"}]},{"repo":"tamerthamoqa/facenet-pytorch-glint360k","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1503.03832"],"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\")"}]},{"repo":"CoinCheung/pytorch-loss","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"JDAI-CV/fast-reid","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":2,"harvested_for":["2105.14432","2108.05045"],"harvested_for_calls":[{"arxiv_id":"2105.14432","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2105.14432"},"call":"get_harvested_code_for_paper(arxiv_id=\"2105.14432\")"},{"arxiv_id":"2108.05045","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2108.05045"},"call":"get_harvested_code_for_paper(arxiv_id=\"2108.05045\")"}]},{"repo":"Recognito-Vision/Android-FaceRecognition-FaceLivenessDetection","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":"601c9a68698e606140de406b2bfa386a1066d707e73d8372a55d3178c0bd9e50","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}