{"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/dsfd-dual-shot-face-detector","title":"DSFD: Dual Shot Face Detector","arxiv_id":"1810.10220","date":"2018-10-24","proceeding":"CVPR 2019 6","authors":["Jian Li","Yabiao Wang","Changan Wang","Ying Tai","Jianjun Qian","Jian Yang","Chengjie Wang","Jilin Li","Feiyue Huang"],"abstract":"In this paper, we propose a novel face detection network with three novel\ncontributions that address three key aspects of face detection, including\nbetter feature learning, progressive loss design and anchor assign based data\naugmentation, respectively. First, we propose a Feature Enhance Module (FEM)\nfor enhancing the original feature maps to extend the single shot detector to\ndual shot detector. Second, we adopt Progressive Anchor Loss (PAL) computed by\ntwo different sets of anchors to effectively facilitate the features. Third, we\nuse an Improved Anchor Matching (IAM) by integrating novel anchor assign\nstrategy into data augmentation to provide better initialization for the\nregressor. Since these techniques are all related to the two-stream design, we\nname the proposed network as Dual Shot Face Detector (DSFD). Extensive\nexperiments on popular benchmarks, WIDER FACE and FDDB, demonstrate the\nsuperiority of DSFD over the state-of-the-art face detectors.","url_abs":"http://arxiv.org/abs/1810.10220v3","url_pdf":"http://arxiv.org/pdf/1810.10220v3.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":"dsfd-dual-shot-face-detector","repo_url":"https://github.com/Tencent/FaceDetection-DSFD","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"dsfd-dual-shot-face-detector","repo_url":"https://github.com/lijiannuist/lightDSFD","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"dsfd-dual-shot-face-detector","repo_url":"https://github.com/code-implementation1/Code3/tree/main/FaceDetection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"dsfd-dual-shot-face-detector","repo_url":"https://github.com/hukkelas/DSFD-Pytorch-Inference","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"face-detection","task_name":"Face Detection"},{"task_slug":"occluded-face-detection","task_name":"Occluded Face Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/face-detection-on-fddb","task":"Face Detection","dataset":"FDDB","model":"DSFD","rank_in_archive_order":1,"of":11,"metrics":{"AP":"0.991"},"uses_additional_data":false},{"leaderboard":"/sota/face-detection-on-wider-face-easy","task":"Face Detection","dataset":"WIDER Face (Easy)","model":"DSFD (RFB)","rank_in_archive_order":9,"of":27,"metrics":{"AP":"0.96"},"uses_additional_data":false},{"leaderboard":"/sota/face-detection-on-wider-face-hard","task":"Face Detection","dataset":"WIDER Face (Hard)","model":"DSFD","rank_in_archive_order":6,"of":40,"metrics":{"AP":"0.9"},"uses_additional_data":false},{"leaderboard":"/sota/face-detection-on-wider-face-hard","task":"Face Detection","dataset":"WIDER Face (Hard)","model":"DSFD (RFB)","rank_in_archive_order":16,"of":40,"metrics":{"AP":"0.872"},"uses_additional_data":false},{"leaderboard":"/sota/face-detection-on-wider-face-medium","task":"Face Detection","dataset":"WIDER Face (Medium)","model":"DSFD","rank_in_archive_order":5,"of":37,"metrics":{"AP":"0.953"},"uses_additional_data":false},{"leaderboard":"/sota/face-detection-on-wider-face-medium","task":"Face Detection","dataset":"WIDER Face (Medium)","model":"DSFD (RFB)","rank_in_archive_order":12,"of":37,"metrics":{"AP":"0.945"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1810.10220","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}