{"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/support-vector-guided-softmax-loss-for-face","title":"Support Vector Guided Softmax Loss for Face Recognition","arxiv_id":"1812.11317","date":"2018-12-29","proceeding":null,"authors":["Xiaobo Wang","Shuo Wang","Shifeng Zhang","Tianyu Fu","Hailin Shi","Tao Mei"],"abstract":"Face recognition has witnessed significant progresses due to the advances of\ndeep convolutional neural networks (CNNs), the central challenge of which, is\nfeature discrimination. To address it, one group tries to exploit mining-based\nstrategies (\\textit{e.g.}, hard example mining and focal loss) to focus on the\ninformative examples. The other group devotes to designing margin-based loss\nfunctions (\\textit{e.g.}, angular, additive and additive angular margins) to\nincrease the feature margin from the perspective of ground truth class. Both of\nthem have been well-verified to learn discriminative features. However, they\nsuffer from either the ambiguity of hard examples or the lack of discriminative\npower of other classes. In this paper, we design a novel loss function, namely\nsupport vector guided softmax loss (SV-Softmax), which adaptively emphasizes\nthe mis-classified points (support vectors) to guide the discriminative\nfeatures learning. So the developed SV-Softmax loss is able to eliminate the\nambiguity of hard examples as well as absorb the discriminative power of other\nclasses, and thus results in more discrimiantive features. To the best of our\nknowledge, this is the first attempt to inherit the advantages of mining-based\nand margin-based losses into one framework. Experimental results on several\nbenchmarks have demonstrated the effectiveness of our approach over\nstate-of-the-arts.","url_abs":"http://arxiv.org/abs/1812.11317v1","url_pdf":"http://arxiv.org/pdf/1812.11317v1.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":"support-vector-guided-softmax-loss-for-face","repo_url":"https://github.com/xiaoboCASIA/SV-X-Softmax","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"support-vector-guided-softmax-loss-for-face","repo_url":"https://github.com/SevenZhan/Pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"support-vector-guided-softmax-loss-for-face","repo_url":"https://github.com/comratvlad/sv_softmax","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"support-vector-guided-softmax-loss-for-face","repo_url":"https://github.com/MindSpore-scientific-2/code-11/tree/main/SV-X-Softmax","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"support-vector-guided-softmax-loss-for-face","repo_url":"https://github.com/Recognito-Vision/Linux-FaceRecognition-FaceLivenessDetection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"face-recognition","task_name":"Face Recognition"}],"methods":[{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/face-identification-on-megaface","task":"Face Identification","dataset":"MegaFace","model":"SV-AM-Softmax","rank_in_archive_order":8,"of":13,"metrics":{"Accuracy":"97.2%"},"uses_additional_data":false},{"leaderboard":"/sota/face-identification-on-trillion-pairs-dataset","task":"Face Identification","dataset":"Trillion Pairs Dataset","model":"SV-AM-Softmax","rank_in_archive_order":1,"of":6,"metrics":{"Accuracy":"73.56"},"uses_additional_data":false},{"leaderboard":"/sota/face-verification-on-megaface","task":"Face Verification","dataset":"MegaFace","model":"SV-AM-Softmax","rank_in_archive_order":7,"of":12,"metrics":{"Accuracy":"97.38%"},"uses_additional_data":false},{"leaderboard":"/sota/face-verification-on-trillion-pairs-dataset","task":"Face Verification","dataset":"Trillion Pairs Dataset","model":"SV-AM-Softmax","rank_in_archive_order":1,"of":6,"metrics":{"Accuracy":"72.71"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1812.11317","atlas_url":"https://app.syntology.ai/?focus=1812.11317","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":"1812.11317"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1812.11317\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1812.11317"},"call":"get_concepts_for_paper(arxiv_id=\"1812.11317\")"}],"by_repo":[{"repo":"xiaoboCASIA/SV-X-Softmax","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"SevenZhan/Pytorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1608.03983"],"harvested_for_calls":[{"arxiv_id":"1608.03983","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1608.03983"},"call":"get_harvested_code_for_paper(arxiv_id=\"1608.03983\")"}]},{"repo":"comratvlad/sv_softmax","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"MindSpore-scientific-2/code-11","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2408.14512"],"harvested_for_calls":[{"arxiv_id":"2408.14512","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2408.14512"},"call":"get_harvested_code_for_paper(arxiv_id=\"2408.14512\")"}]},{"repo":"Recognito-Vision/Linux-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":"8b7287b4391302fee053b7d7d321edc1568f31192714c86d86a0517444ef00bf","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}