{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/detecting-faces-using-region-based-fully","title":"Detecting Faces Using Region-based Fully Convolutional Networks","arxiv_id":"1709.05256","date":"2017-09-14","proceeding":null,"authors":["Yitong Wang","Xing Ji","Zheng Zhou","Hao Wang","Zhifeng Li"],"abstract":"Face detection has achieved great success using the region-based methods. In\nthis report, we propose a region-based face detector applying deep networks in\na fully convolutional fashion, named Face R-FCN. Based on Region-based Fully\nConvolutional Networks (R-FCN), our face detector is more accurate and\ncomputational efficient compared with the previous R-CNN based face detectors.\nIn our approach, we adopt the fully convolutional Residual Network (ResNet) as\nthe backbone network. Particularly, We exploit several new techniques including\nposition-sensitive average pooling, multi-scale training and testing and\non-line hard example mining strategy to improve the detection accuracy. Over\ntwo most popular and challenging face detection benchmarks, FDDB and WIDER\nFACE, Face R-FCN achieves superior performance over state-of-the-arts.","url_abs":"http://arxiv.org/abs/1709.05256v2","url_pdf":"http://arxiv.org/pdf/1709.05256v2.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":"detecting-faces-using-region-based-fully","repo_url":"https://github.com/vikramkarthikeyan/Face-R-FCN","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":null,"task_name":"Position"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"position-sensitive-roi-pooling","method_name":"Position-Sensitive RoI Pooling"},{"method_slug":"r-fcn","method_name":"R-FCN"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/face-detection-on-fddb","task":"Face Detection","dataset":"FDDB","model":"Face R-FCN","rank_in_archive_order":2,"of":11,"metrics":{"AP":"0.990"},"uses_additional_data":false},{"leaderboard":"/sota/face-detection-on-wider-face-easy","task":"Face Detection","dataset":"WIDER Face (Easy)","model":"Face R-FCN","rank_in_archive_order":19,"of":27,"metrics":{"AP":"0.943"},"uses_additional_data":false},{"leaderboard":"/sota/face-detection-on-wider-face-hard","task":"Face Detection","dataset":"WIDER Face (Hard)","model":"Face R-FCN","rank_in_archive_order":11,"of":40,"metrics":{"AP":"0.876"},"uses_additional_data":false},{"leaderboard":"/sota/face-detection-on-wider-face-medium","task":"Face Detection","dataset":"WIDER Face (Medium)","model":"Face R-FCN","rank_in_archive_order":19,"of":37,"metrics":{"AP":"0.931"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1709.05256","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}