Unsupervised Domain Adaptation for Face Anti-Spoofing
Unsupervised Domain Adaptation for Face Anti-Spoofing
复制标题
人脸防欺骗的无监督域自适应
DOI：
10.1109/tifs.2018.2801312
复制
发表时间：
2018-07-01
影响因子：
6.8
通讯作者：
Kot, Alex C.
中科院分区：
文献类型：
--
作者：
Li, Haoliang;Li, Wen;Kot, Alex C.
面部防欺骗（又名由于移动的电话、PC、平板电脑等上的用户认证需求的快速增长，最近已经出现作为对学术界和工业界具有重大意义的活跃话题。最近，已经基于训练样本和测试样本在特征空间和边际概率分布方面处于相同域的假设提出了许多面部欺骗检测方案。然而，由于在人脸获取中的主导条件（光照、面部外观、相机质量等）的无限变化，这种单域方法缺乏泛化能力，这进一步阻碍了它们在实际应用中的应用。有鉴于此，我们引入了一种无监督的域自适应人脸反欺骗方案，以解决现实世界中的场景，该场景基于不同源域中的训练样本学习目标域的分类器。特别地，首先基于源和目标域数据施加嵌入函数，其将数据映射到可以测量分布相似性的新空间。随后，源域和目标域中的潜在特征之间的最大平均离散度被最小化，使得可以学习更通用的分类器。该框架进一步采用了最先进的表示方法，包括手工制作和深度神经网络学习的特征，以探索它们在领域适应中的能力。此外，我们引入了一个新的人脸欺骗检测数据库，其中包含了大量的欺骗类型，捕获设备，照明，等各种各样的人脸样本超过4000在现有的基准数据库和新的数据库上进行了大量的实验验证，所提出的方法可以获得更好的泛化能力，在跨域的情况下，通过提供一致的更好的反欺骗性能。
Face anti-spoofing (a.k.a. presentation attack detection) has recently emerged as an active topic with great significance for both academia and industry due to the rapidly increasing demand in user authentication on mobile phones, PCs, tablets, and so on. Recently, numerous face spoofing detection schemes have been proposed based on the assumption that training and testing samples are in the same domain in terms of the feature space and marginal probability distribution. However, due to unlimited variations of the dominant conditions (illumination, facial appearance, camera quality, and so on) in face acquisition, such single domain methods lack generalization capability, which further prevents them from being applied in practical applications. In light of this, we introduce an unsupervised domain adaptation face anti-spoofing scheme to address the real-world scenario that learns the classifier for the target domain based on training samples in a different source domain. In particular, an embedding function is first imposed based on source and target domain data, which maps the data to a new space where the distribution similarity can be measured. Subsequently, the Maximum Mean Discrepancy between the latent features in source and target domains is minimized such that a more generalized classifier can be learned. State-of-the-art representations including both hand-crafted and deep neural network learned features are further adopted into the framework to quest the capability of them in domain adaptation. Moreover, we introduce a new database for face spoofing detection, which contains more than 4000 face samples with a large variety of spoofing types, capture devices, illuminations, and so on. Extensive experiments on existing benchmark databases and the new database verify that the proposed approach can gain significantly better generalization capability in cross-domain scenarios by providing consistently better anti-spoofing performance.