{"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/one-shot-face-recognition-by-promoting","title":"One-shot Face Recognition by Promoting Underrepresented Classes","arxiv_id":"1707.05574","date":"2017-07-18","proceeding":null,"authors":["Yandong Guo","Lei Zhang"],"abstract":"In this paper, we study the problem of training large-scale face\nidentification model with imbalanced training data. This problem naturally\nexists in many real scenarios including large-scale celebrity recognition,\nmovie actor annotation, etc. Our solution contains two components. First, we\nbuild a face feature extraction model, and improve its performance, especially\nfor the persons with very limited training samples, by introducing a\nregularizer to the cross entropy loss for the multi-nomial logistic regression\n(MLR) learning. This regularizer encourages the directions of the face features\nfrom the same class to be close to the direction of their corresponding\nclassification weight vector in the logistic regression. Second, we build a\nmulti-class classifier using MLR on top of the learned face feature extraction\nmodel. Since the standard MLR has poor generalization capability for the\none-shot classes even if these classes have been oversampled, we propose a\nnovel supervision signal called underrepresented-classes promotion loss, which\naligns the norms of the weight vectors of the one-shot classes (a.k.a.\nunderrepresented-classes) to those of the normal classes. In addition to the\noriginal cross entropy loss, this new loss term effectively promotes the\nunderrepresented classes in the learned model and leads to a remarkable\nimprovement in face recognition performance.\n  We test our solution on the MS-Celeb-1M low-shot learning benchmark task. Our\nsolution recognizes 94.89% of the test images at the precision of 99\\% for the\none-shot classes. To the best of our knowledge, this is the best performance\namong all the published methods using this benchmark task with the same setup,\nincluding all the participants in the recent MS-Celeb-1M challenge at ICCV\n2017.","url_abs":"http://arxiv.org/abs/1707.05574v2","url_pdf":"http://arxiv.org/pdf/1707.05574v2.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":"one-shot-face-recognition-by-promoting","repo_url":"https://github.com/SimonLliu/CSS_and_up_term","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"face-identification","task_name":"Face Identification"},{"task_slug":"face-recognition","task_name":"Face Recognition"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"SimonLliu/CSS_and_up_term","kind":"listed","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":"690c4b260c56dcc434b43af91c86e5a56eb19521e4de965ef359e82ccbf8663c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}