Inspired by the philosophy employed by human beings to determine whether a presented face example is genuine or not, i.e., to glance at the example globally first and then carefully observe the local regions to gain more discriminative information, for the face anti-spoofing problem, we propose a novel framework based on the Convolutional Neural Network (CNN) and the Recurrent Neural Network (RNN). In particular, we model the behavior of exploring face-spoofing-related information from image sub-patches by leveraging deep reinforcement learning. We further introduce a recurrent mechanism to learn representations of local information sequentially from the explored sub-patches with an RNN. Finally, for the classification purpose, we fuse the local information with the global one, which can be learned from the original input image through a CNN. Moreover, we conduct extensive experiments, including ablation study and visualization analysis, to evaluate our proposed framework on various public databases. The experiment results show that our method can generally achieve state-of-the-art performance among all scenarios, demonstrating its effectiveness.
Learning Meta Model for Zero- and Few-shot Face Anti-spoofing
Northwestern Polytechnical University(西北工业大学);AIBEE;National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Science(中国科学院自动化研究所模式识别国家重点实验室);Winsense Technology Ltd(文思海辉技术有限公司);University of Oulu(奥卢大学)
Great Bay University(大湾区大学);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);SailYond Technology(赛扬科技);University of Oulu(奥卢大学);Nanjing University of Information Science and Technology(南京信息工程大学)
University of Oulu(奥卢大学);Chinese Academy of Sciences(中国科学院);Institute of Computing Technology, CAS(中国科学院计算技术研究所);University of Chinese Academy of Sciences(中国科学院大学);Xi’an Jiaotong University(西安交通大学)
NAS-FAS: Static-Dynamic Central Difference Network Search for Face Anti-Spoofing
University of Oulu(奥卢大学);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);University of Chinese Academy of Sciences(中国科学院大学);Northwestern Polytechnical University(西北工业大学);Westlake University(西湖大学)
Confidence Aware Learning for Reliable Face Anti-spoofing
Key Laboratory of AI Safety of CAS, Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS)(中国科学院计算技术研究所人工智能安全重点实验室);University of Chinese Academy of Sciences (UCAS)(中国科学院大学)
Learning deep forest with multi-scale Local Binary Pattern features for face anti-spoofing
Nanyang Technological University(南洋理工大学);Shenzhen University(深圳大学);Shenzhen Institute of Artificial Intelligence and Robotics for Society(深圳人工智能与机器人研究院)
Revisiting Pixel-Wise Supervision for Face Anti-Spoofing
Center for Machine Vision and Signal Analysis, University of Oulu(奥卢大学机器视觉与信号分析中心);Xi’an Jiaotong University(西安交通大学);Northwestern Polytechnical University(西北工业大学)
IFAST: Weakly Supervised Interpretable Face Anti-spoofing from Single-shot Binocular NIR Images
Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院);University of Chinese Academy of Sciences(中国科学院大学);The Chinese University of Hong Kong(香港中文大学)
Nanyang Technological University(南洋理工大学);Agency for Science, Technology and Research (A*STAR)(新加坡科技研究局);University of Oulu(奥卢大学);Great Bay University(大湾区大学);Great Bay Institute for Advanced Study(大湾区高等研究院);South China University of Technology(华南理工大学)
Consistency Regularization for Deep Face Anti-Spoofing
Kuaishou Technology(快手科技);University of Oulu(奥卢大学);Communication University of China(中国传媒大学);Academy of Sciences, Mininglamp Technology(明略科技集团科学院);CBSR&NLPR, CASIA(中国科学院自动化研究所);Lappeenranta-Lahti University of Technology(拉彭兰塔-拉赫蒂理工大学)
Multi-Modal Face Anti-Spoofing Based on Central Difference Networks
University of Oulu(奥卢大学);Northwestern Polytechnical University(西北工业大学);Mininglamp Academy of Sciences, Mininglamp Technology(明略科技集团明略科学院);Authenmetric(中科博宏)
DiffFAS: Face Anti-Spoofing via Generative Diffusion Models
Tianjin University(天津大学);Lappeenranta-Lahti University of Technology LUT(拉彭兰塔-拉赫蒂理工大学LUT);Great Bay University(大湾区大学);Xi’an Jiaotong University(西安交通大学)
University of Oulu(奥卢大学);Communication University of China(中国传媒大学);SailYond Technology(赛扬德科技);Institute of Automation, Chinese Academy of Sciences (CASIA)(中国科学院自动化研究所);University of Chinese Academy of Sciences (UCAS)(中国科学院大学);Hong Kong Institute of Science & Innovation, Chinese Academy of Sciences(中国科学院香港创新研究院)
BIG-MoE: Bypass Isolated Gating MoE for Generalized Multimodal Face Anti-Spoofing
College of Computer Science and Software Engineering, Shenzhen University(深圳大学计算机与软件学院);Great Bay University(大湾区大学);National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University(深圳大学大数据系统计算技术国家工程实验室);Guangdong Provincial Key Laboratory of Intelligent Information Processing(广东省智能信息处理重点实验室)
Great Bay University(大湾区大学);Nanyang Technological University(南洋理工大学);University of Oulu(奥卢大学);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);University of Chinese Academy of Sciences(中国科学院大学);Shenzhen University(深圳大学)
Rethinking Vision Transformer and Masked Autoencoder in Multimodal Face Anti-Spoofing
Great Bay University(大湾区大学);Nanyang Technological University(南洋理工大学);University of Oulu(奥卢大学);Lappeenranta-Lahti University of Technology(拉彭兰塔-拉赫蒂理工大学);South China University of Technology(华南理工大学)
近年来,基于视觉Transformer(ViT)的多模态学习方法被提出来提高人脸反欺骗(FAS)系统的鲁棒性。然而,仍然没有工作来探索的基本性质(\textit{e.g.},模态感知输入,合适的多模态预训练,和有效的微调),在香草ViT多模态FAS。在本文中,我们研究了三个关键因素(即,输入、预训练和微调),用于具有RGB、红外(IR)和深度的多模态FAS。首先,在ViT输入方面,我们发现利用局部特征描述符有利于IR模态上的ViT,而不是RGB或深度模态。其次,在观察的效率直接微调整个或部分ViT,我们设计了一个自适应多模态适配器(AMA),它可以有效地聚合本地多模态功能,同时冻结大多数ViT参数。最后,考虑到任务(FAS与通用对象分类)和模态(多模态与单峰)的差距,ImageNet预训练模型对于多模态FAS任务可能是次优的。为了弥合这些差距,我们提出了模态非对称掩码自编码器(M $^{2}$ A $^{2}$ E),用于多模态FAS自监督预训练,而无需昂贵的注释标签。与先前的模态对称自动编码器相比,所提出的M $^{2}$ A $^{2}$ E能够学习更多内在的任务感知表示并且与模态不可知(例如,单峰、双峰和三峰)下游设置。在多模态FAS基准上进行的单峰(RGB,深度,IR)和多模态(RGB+深度,RGB+IR,深度+IR,RGB+深度+IR)设置的广泛实验证明了所提出的方法的优…
Learning Generalizable and Identity-Discriminative Representations for Face Anti-Spoofing
University of Electronic Science and Technology of China(电子科技大学);National University of Singapore(新加坡国立大学);National University of Defense Technology(国防科技大学)
Robust Multi-Modal Face Anti-Spoofing with Domain Adaptation: Tackling Missing Modalities, Noisy Pseudo-Labels, and Model Degradation
College of Computer and Cyber Security, Fujian Normal University(计算机与网络安全部,福建师范大学);Department of Computer Science, National Tsing Hua University(计算机科学系,国立清华大学)
Spoof Trace Discovery for Deep Learning Based Explainable Face Anti-Spoofing
School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院);MAIS, Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所MAIS);China Mobile Financial Technology Co., Ltd.(中国移动金融科技有限公司);Guangzhou Pixel Solutions Co., Ltd.(广州像素解决方案有限公司);Center for Machine Vision and Signal Analysis, University of Oulu(奥卢大学机器视觉与信号分析中心);CAIR, HKSIS, Chinese Academy of Sciences(中国科学院香港创新研究所有限公司);SCSE, the Faculty of Innovation Engineering, M.U.S.T(澳门创新工程学院SCSE)
Adversarial Attacks on Both Face Recognition and Face Anti-spoofing Models
School of Computer Science and Technology, Huazhong University of Science and Technology(华中科技大学计算机科学与技术学院);College of Computer Science and Technology, Jilin University(吉林大学计算机科学与技术学院);Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, JLU(教育部符号计算与知识工程重点实验室);Department of Computer Science and Software Engineering, The University of Western Australia(西澳大学计算机科学与软件工程系)
Communication University of China(中国传媒大学);Northwestern Polytechnical University(西北工业大学);University of Oulu(奥卢大学);Beijing Kwai Technology Co., Ltd(北京快手科技有限公司);MiningLamp Technology(明略科技);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);University of Chinese Academy of Sciences(中国科学院大学);Hong Kong Institute of Science & Innovation, Chinese Academy of Sciences(中国科学院香港创新研究院)
Face Anti-Spoofing(FAS)保护面部识别免受演示攻击(PA)。现有的FAS方法通常用手工制作的二进制或像素标签来监督PA检测器。然而,手工制作的标签可能不是监督PA检测器学习足够的和内在的欺骗线索的最适当的方式。而不是使用手工制作的标签,我们提出了一种新的元教师FAS(MT-FAS)方法训练元教师监督PA检测器更有效。元教师以双级优化的方式被训练以学习监督PA检测器学习丰富的欺骗线索的能力。双层优化包含两个关键组成部分:1)较低级别的训练,其中元教师监督检测器在训练集上的学习过程;以及2)较高级别的训练,其中元教师的教学性能通过最小化检测器的验证损失来优化。我们的元教师与现有的师生模型有很大的不同,因为元教师是为了更好地教授检测器(学生)而明确训练的,而现有的教师则是为了突出的准确性而忽略教学能力而训练的。在五个FAS基准测试上的广泛实验表明,使用所提出的MT-FAS,经过训练的元教师1)提供比手工制作的标签和现有的师生模型更适合的监督; 2)显着提高PA检测器的性能。