{"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/selective-refinement-network-for-high","title":"Selective Refinement Network for High Performance Face Detection","arxiv_id":"1809.02693","date":"2018-09-07","proceeding":null,"authors":["Cheng Chi","Shifeng Zhang","Junliang Xing","Zhen Lei","Stan Z. Li","Xudong Zou"],"abstract":"High performance face detection remains a very challenging problem,\nespecially when there exists many tiny faces. This paper presents a novel\nsingle-shot face detector, named Selective Refinement Network (SRN), which\nintroduces novel two-step classification and regression operations selectively\ninto an anchor-based face detector to reduce false positives and improve\nlocation accuracy simultaneously. In particular, the SRN consists of two\nmodules: the Selective Two-step Classification (STC) module and the Selective\nTwo-step Regression (STR) module. The STC aims to filter out most simple\nnegative anchors from low level detection layers to reduce the search space for\nthe subsequent classifier, while the STR is designed to coarsely adjust the\nlocations and sizes of anchors from high level detection layers to provide\nbetter initialization for the subsequent regressor. Moreover, we design a\nReceptive Field Enhancement (RFE) block to provide more diverse receptive\nfield, which helps to better capture faces in some extreme poses. As a\nconsequence, the proposed SRN detector achieves state-of-the-art performance on\nall the widely used face detection benchmarks, including AFW, PASCAL face,\nFDDB, and WIDER FACE datasets. Codes will be released to facilitate further\nstudies on the face detection problem.","url_abs":"http://arxiv.org/abs/1809.02693v1","url_pdf":"http://arxiv.org/pdf/1809.02693v1.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":"selective-refinement-network-for-high","repo_url":"https://github.com/ChiCheng123/SRN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"selective-refinement-network-for-high","repo_url":"https://github.com/faridSam/srn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"selective-refinement-network-for-high","repo_url":"https://github.com/glarbi/Face-detection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"face-detection","task_name":"Face Detection"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"high","task_name":"Vocal Bursts Intensity Prediction"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/face-detection-on-annotated-faces-in-the-wild","task":"Face Detection","dataset":"Annotated Faces in the Wild","model":"SRN","rank_in_archive_order":1,"of":7,"metrics":{"AP":"0.9987"},"uses_additional_data":false},{"leaderboard":"/sota/face-detection-on-fddb","task":"Face Detection","dataset":"FDDB","model":"SRN","rank_in_archive_order":3,"of":11,"metrics":{"AP":"0.988"},"uses_additional_data":false},{"leaderboard":"/sota/face-detection-on-pascal-face","task":"Face Detection","dataset":"PASCAL Face","model":"SRN","rank_in_archive_order":1,"of":6,"metrics":{"AP":"0.9909"},"uses_additional_data":false},{"leaderboard":"/sota/face-detection-on-wider-face-easy","task":"Face Detection","dataset":"WIDER Face (Easy)","model":"SRN","rank_in_archive_order":10,"of":27,"metrics":{"AP":"0.959"},"uses_additional_data":false},{"leaderboard":"/sota/face-detection-on-wider-face-hard","task":"Face Detection","dataset":"WIDER Face (Hard)","model":"SRN","rank_in_archive_order":9,"of":40,"metrics":{"AP":"0.896"},"uses_additional_data":false},{"leaderboard":"/sota/face-detection-on-wider-face-medium","task":"Face Detection","dataset":"WIDER Face (Medium)","model":"SRN","rank_in_archive_order":10,"of":37,"metrics":{"AP":"0.948"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1809.02693","atlas_url":"https://app.syntology.ai/?focus=1809.02693","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":"1809.02693"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1809.02693\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1809.02693"},"call":"get_concepts_for_paper(arxiv_id=\"1809.02693\")"}],"by_repo":[{"repo":"ChiCheng123/SRN","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"faridSam/srn","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"glarbi/Face-detection","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":"b940317497f3a05ee3d003f75bb86b3ddce5d45513e119c1c40865e5c1ec8484","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}