{"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/s3fd-single-shot-scale-invariant-face","title":"S$^3$FD: Single Shot Scale-invariant Face Detector","arxiv_id":"1708.05237","date":"2017-08-17","proceeding":null,"authors":["Shifeng Zhang","Xiangyu Zhu","Zhen Lei","Hailin Shi","Xiaobo Wang","Stan Z. Li"],"abstract":"This paper presents a real-time face detector, named Single Shot\nScale-invariant Face Detector (S$^3$FD), which performs superiorly on various\nscales of faces with a single deep neural network, especially for small faces.\nSpecifically, we try to solve the common problem that anchor-based detectors\ndeteriorate dramatically as the objects become smaller. We make contributions\nin the following three aspects: 1) proposing a scale-equitable face detection\nframework to handle different scales of faces well. We tile anchors on a wide\nrange of layers to ensure that all scales of faces have enough features for\ndetection. Besides, we design anchor scales based on the effective receptive\nfield and a proposed equal proportion interval principle; 2) improving the\nrecall rate of small faces by a scale compensation anchor matching strategy; 3)\nreducing the false positive rate of small faces via a max-out background label.\nAs a consequence, our method achieves state-of-the-art detection performance on\nall the common face detection benchmarks, including the AFW, PASCAL face, FDDB\nand WIDER FACE datasets, and can run at 36 FPS on a Nvidia Titan X (Pascal) for\nVGA-resolution images.","url_abs":"http://arxiv.org/abs/1708.05237v3","url_pdf":"http://arxiv.org/pdf/1708.05237v3.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":"s3fd-single-shot-scale-invariant-face","repo_url":"https://github.com/sfzhang15/SFD","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"s3fd-single-shot-scale-invariant-face","repo_url":"https://github.com/LeeRel1991/SFD","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"s3fd-single-shot-scale-invariant-face","repo_url":"https://github.com/yxlijun/s3fd.pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"face-detection","task_name":"Face Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/face-detection-on-fddb","task":"Face Detection","dataset":"FDDB","model":"S3FD","rank_in_archive_order":5,"of":11,"metrics":{"AP":"0.983"},"uses_additional_data":false},{"leaderboard":"/sota/face-detection-on-pascal-face","task":"Face Detection","dataset":"PASCAL Face","model":"S3FD","rank_in_archive_order":2,"of":6,"metrics":{"AP":"0.9849"},"uses_additional_data":false},{"leaderboard":"/sota/face-detection-on-wider-face-easy","task":"Face Detection","dataset":"WIDER Face (Easy)","model":"S3FD(F+S+M)","rank_in_archive_order":21,"of":27,"metrics":{"AP":"0.937"},"uses_additional_data":false},{"leaderboard":"/sota/face-detection-on-wider-face-hard","task":"Face Detection","dataset":"WIDER Face (Hard)","model":"S3FD(F+S+M)","rank_in_archive_order":20,"of":40,"metrics":{"AP":"0.852"},"uses_additional_data":false},{"leaderboard":"/sota/face-detection-on-wider-face-medium","task":"Face Detection","dataset":"WIDER Face (Medium)","model":"S3FD(F+S+M)","rank_in_archive_order":21,"of":37,"metrics":{"AP":"0.924"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1708.05237","atlas_url":"https://app.syntology.ai/?focus=1708.05237","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":"1708.05237"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1708.05237\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1708.05237"},"call":"get_concepts_for_paper(arxiv_id=\"1708.05237\")"}],"by_repo":[{"repo":"sfzhang15/SFD","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"LeeRel1991/SFD","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"yxlijun/s3fd.pytorch","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":"c6821e022c7237c59c55ee5493a152237644da0f9caf3def91f4babbc2eec50e","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}