{"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/pyramidbox-a-context-assisted-single-shot","title":"PyramidBox: A Context-assisted Single Shot Face Detector","arxiv_id":"1803.07737","date":"2018-03-21","proceeding":"ECCV 2018 9","authors":["Xu Tang","Daniel K. Du","Zeqiang He","Jingtuo Liu"],"abstract":"Face detection has been well studied for many years and one of remaining\nchallenges is to detect small, blurred and partially occluded faces in\nuncontrolled environment. This paper proposes a novel context-assisted single\nshot face detector, named \\emph{PyramidBox} to handle the hard face detection\nproblem. Observing the importance of the context, we improve the utilization of\ncontextual information in the following three aspects. First, we design a novel\ncontext anchor to supervise high-level contextual feature learning by a\nsemi-supervised method, which we call it PyramidAnchors. Second, we propose the\nLow-level Feature Pyramid Network to combine adequate high-level context\nsemantic feature and Low-level facial feature together, which also allows the\nPyramidBox to predict faces of all scales in a single shot. Third, we introduce\na context-sensitive structure to increase the capacity of prediction network to\nimprove the final accuracy of output. In addition, we use the method of\nData-anchor-sampling to augment the training samples across different scales,\nwhich increases the diversity of training data for smaller faces. By exploiting\nthe value of context, PyramidBox achieves superior performance among the\nstate-of-the-art over the two common face detection benchmarks, FDDB and WIDER\nFACE. Our code is available in PaddlePaddle:\n\\href{https://github.com/PaddlePaddle/models/tree/develop/fluid/face_detection}{\\url{https://github.com/PaddlePaddle/models/tree/develop/fluid/face_detection}}.","url_abs":"http://arxiv.org/abs/1803.07737v2","url_pdf":"http://arxiv.org/pdf/1803.07737v2.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":"pyramidbox-a-context-assisted-single-shot","repo_url":"https://github.com/PaddlePaddle/models","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"paddle","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"pyramidbox-a-context-assisted-single-shot","repo_url":"https://github.com/EricZgw/PyramidBox","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"pyramidbox-a-context-assisted-single-shot","repo_url":"https://github.com/Swybino/PotatoNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"pyramidbox-a-context-assisted-single-shot","repo_url":"https://github.com/goingqs/pyramidbox","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"pyramidbox-a-context-assisted-single-shot","repo_url":"https://github.com/2023-MindSpore-1/ms-code-216/tree/main/PyramidBox","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"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":"PyramidBox","rank_in_archive_order":4,"of":11,"metrics":{"AP":"0.987"},"uses_additional_data":false},{"leaderboard":"/sota/face-detection-on-wider-face-easy","task":"Face Detection","dataset":"WIDER Face (Easy)","model":"PyramidBox","rank_in_archive_order":7,"of":27,"metrics":{"AP":"0.961"},"uses_additional_data":false},{"leaderboard":"/sota/face-detection-on-wider-face-hard","task":"Face Detection","dataset":"WIDER Face (Hard)","model":"PyramidBox","rank_in_archive_order":10,"of":40,"metrics":{"AP":"0.889"},"uses_additional_data":false},{"leaderboard":"/sota/face-detection-on-wider-face-medium","task":"Face Detection","dataset":"WIDER Face (Medium)","model":"PyramidBox","rank_in_archive_order":11,"of":37,"metrics":{"AP":"0.946"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1803.07737","atlas_url":"https://app.syntology.ai/?focus=1803.07737","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}