基于条件对抗域泛化的人脸活体检测方法  

Face anti-spoofing method based on conditional adversarial domain generalization

作　　者：蔡体健[1] 尘福春 刘文鑫 Cai Tijian;Chen Fuchun;Liu Wenxin(School of Information Engineering,East China Jiaotong University,Nanchang 330013,China)

机构地区：[1]华东交通大学信息工程学院,南昌330013

出　　处：《计算机应用研究》2022年第8期2538-2544,共7页Application Research of Computers

基　　金：国家自然科学基金资助项目(62166018);江西省重点研发计划资助项目(20203BBE53029);江西省高等学校教学改革重点研究课题(JXJG-20-5-6)。

摘　　要：针对现存的跨场景人脸活体检测模型泛化性能差、类间重叠等问题,提出了一种基于条件对抗域泛化的人脸活体检测方法。首先,该方法使用嵌入注意力机制的U-Net和ResNet-18编码器提取多个源域的特征,然后将提取的特征送入辅助分类器,并将特征编码器的输出和分类器预测的结果通过多线性映射的方法进行融合,再输入到域判别器中进行对抗训练,以实现特征和类层面对齐多个源域。其次,为了减少预测不准确的难迁移样本对域泛化造成的影响,采用了熵函数来控制样本的优先级,以提高域泛化的性能。此外,通过添加人脸深度图以进一步抓取活体与假体的区别特征,通过非对称三元组损失约束作为辅助监督,进一步提高类内紧凑性和类间区分性。在公开活体检测数据集上的对比实验验证了所提方法的有效性。Aiming at the problems of poor generalization performance and overlapping between classes of existing cross scene face anti-spoofing detection models,this paper proposed a face anti-spoofing method based on conditional adversarial domain generalization.Firstly,the method used U-Net embedded with attention mechanism and ResNet-18 encoder to extract features from multiple source domains,then sent the extracted features to auxiliary classifier,and combined the output of the feature encoder with the prediction results of the classifier by the method of multilinear mapping,and then input into the domain discriminator for adversarial training to achieve feature and class-level alignment of multiple source domains.Secondly,in order to reduce the impact of difficult to transfer samples with inaccurate prediction on domain generalization,this paper used entropy function to control the priority of samples to improve the performance of domain generalization.In addition,by adding a face depth map to further capture the distinguishing features of the real and attack face,and using asymmetric triplet loss constraint as auxiliary supervision to further improve the intra-class compactness and inter-class discrimination.Comparative experiments on public live detection datasets verify the effectiveness of the proposed method.

关 键 词：人脸活体检测 域泛化 多线性映射 熵函数 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]