{"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/ssh-single-stage-headless-face-detector","title":"SSH: Single Stage Headless Face Detector","arxiv_id":"1708.03979","date":"2017-08-14","proceeding":"ICCV 2017 10","authors":["Mahyar Najibi","Pouya Samangouei","Rama Chellappa","Larry Davis"],"abstract":"We introduce the Single Stage Headless (SSH) face detector. Unlike two stage\nproposal-classification detectors, SSH detects faces in a single stage directly\nfrom the early convolutional layers in a classification network. SSH is\nheadless. That is, it is able to achieve state-of-the-art results while\nremoving the \"head\" of its underlying classification network -- i.e. all fully\nconnected layers in the VGG-16 which contains a large number of parameters.\nAdditionally, instead of relying on an image pyramid to detect faces with\nvarious scales, SSH is scale-invariant by design. We simultaneously detect\nfaces with different scales in a single forward pass of the network, but from\ndifferent layers. These properties make SSH fast and light-weight.\nSurprisingly, with a headless VGG-16, SSH beats the ResNet-101-based\nstate-of-the-art on the WIDER dataset. Even though, unlike the current\nstate-of-the-art, SSH does not use an image pyramid and is 5X faster. Moreover,\nif an image pyramid is deployed, our light-weight network achieves\nstate-of-the-art on all subsets of the WIDER dataset, improving the AP by 2.5%.\nSSH also reaches state-of-the-art results on the FDDB and Pascal-Faces datasets\nwhile using a small input size, leading to a runtime of 50 ms/image on a GPU.\nThe code is available at https://github.com/mahyarnajibi/SSH.","url_abs":"http://arxiv.org/abs/1708.03979v3","url_pdf":"http://arxiv.org/pdf/1708.03979v3.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":"ssh-single-stage-headless-face-detector","repo_url":"https://github.com/mahyarnajibi/SSH","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"ssh-single-stage-headless-face-detector","repo_url":"https://github.com/RangiLyu/mmdetection_test","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"ssh-single-stage-headless-face-detector","repo_url":"https://github.com/anhtu293/Vietnamese-Celebrity-Face-Recognition","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"ssh-single-stage-headless-face-detector","repo_url":"https://github.com/open-mmlab/mmdetection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"ssh-single-stage-headless-face-detector","repo_url":"https://github.com/starimpact/arm_SNIPER","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"ssh-single-stage-headless-face-detector","repo_url":"https://github.com/stephenkung/NIR_VIS_Face_Recognition","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"classification","task_name":"General Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1708.03979","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}