{"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-high-performance-detector-for","title":"PyramidBox++: High Performance Detector for Finding Tiny Face","arxiv_id":"1904.00386","date":"2019-03-31","proceeding":null,"authors":["Zhihang Li","Xu Tang","Junyu Han","Jingtuo Liu","Ran He"],"abstract":"With the rapid development of deep convolutional neural network, face\ndetection has made great progress in recent years. WIDER FACE dataset, as a\nmain benchmark, contributes greatly to this area. A large amount of methods\nhave been put forward where PyramidBox designs an effective data augmentation\nstrategy (Data-anchor-sampling) and context-based module for face detector. In\nthis report, we improve each part to further boost the performance, including\nBalanced-data-anchor-sampling, Dual-PyramidAnchors and Dense Context Module.\nSpecifically, Balanced-data-anchor-sampling obtains more uniform sampling of\nfaces with different sizes. Dual-PyramidAnchors facilitate feature learning by\nintroducing progressive anchor loss. Dense Context Module with dense connection\nnot only enlarges receptive filed, but also passes information efficiently.\nIntegrating these techniques, PyramidBox++ is constructed and achieves\nstate-of-the-art performance in hard set.","url_abs":"http://arxiv.org/abs/1904.00386v1","url_pdf":"http://arxiv.org/pdf/1904.00386v1.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-high-performance-detector-for","repo_url":"https://github.com/2023-MindSpore-4/Code6/tree/main/PyramidBox","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"pyramidbox-high-performance-detector-for","repo_url":"https://github.com/Mind23-2/MindCode-5/tree/main/PyramidBox","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"pyramidbox-high-performance-detector-for","repo_url":"https://github.com/MindSpore-paper-code-2/code2/tree/main/PyramidBox","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"pyramidbox-high-performance-detector-for","repo_url":"https://github.com/code-implementation1/Code6/tree/main/PyramidBox","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"face-detection","task_name":"Face Detection"},{"task_slug":"high","task_name":"Vocal Bursts Intensity Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.00386","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}