{"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/learning-deep-models-for-face-anti-spoofing","title":"Learning Deep Models for Face Anti-Spoofing: Binary or Auxiliary Supervision","arxiv_id":"1803.11097","date":"2018-03-29","proceeding":"CVPR 2018 6","authors":["Yaojie Liu","Amin Jourabloo","Xiaoming Liu"],"abstract":"Face anti-spoofing is the crucial step to prevent face recognition systems\nfrom a security breach. Previous deep learning approaches formulate face\nanti-spoofing as a binary classification problem. Many of them struggle to\ngrasp adequate spoofing cues and generalize poorly. In this paper, we argue the\nimportance of auxiliary supervision to guide the learning toward discriminative\nand generalizable cues. A CNN-RNN model is learned to estimate the face depth\nwith pixel-wise supervision, and to estimate rPPG signals with sequence-wise\nsupervision. Then we fuse the estimated depth and rPPG to distinguish live vs.\nspoof faces. In addition, we introduce a new face anti-spoofing database that\ncovers a large range of illumination, subject, and pose variations.\nExperimental results show that our model achieves the state-of-the-art\nperformance on both intra-database and cross-database testing.","url_abs":"http://arxiv.org/abs/1803.11097v1","url_pdf":"http://arxiv.org/pdf/1803.11097v1.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":[],"tasks":[{"task_slug":"binary-classification","task_name":"Binary Classification"},{"task_slug":"face-anti-spoofing","task_name":"Face Anti-Spoofing"},{"task_slug":"face-recognition","task_name":"Face Recognition"},{"task_slug":"classification","task_name":"General Classification"}],"methods":[],"datasets_introduced":[{"slug":"siw","name":"SiW","full_name":"Spoofing in the Wild"}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1803.11097","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}