Abstract
Face recognition has achieved unprecedented results, surpassing human capabilities in certain scenarios. However, these automatic solutions are not ready for production because they can be easily fooled by simple identity impersonation attacks. And although much effort has been devoted to develop face anti-spoofing models, their generalization capacity still remains a challenge in real scenarios. In this paper, we introduce a novel approach that reformulates the Generalized Presentation Attack Detection (GPAD) problem from an anomaly detection perspective. Technically, a deep metric learning model is proposed, where a triplet focal loss is used as a regularization for a novel loss coined "metric-softmax", which is in charge of guiding the learning process towards more discriminative feature representations in an embedding space. Finally, we demonstrate the benefits of our deep anomaly detection architecture, by introducing a few-shot a posteriori probability estimation that does not need any classifier to be trained on the learned features. We conduct extensive experiments using the GRAD-GPAD framework that provides the largest aggregated dataset for face GPAD. Results confirm that our approach is able to outperform all the state-of-the-art methods by a considerable margin.
Abstract (translated)
人脸识别取得了前所未有的效果，在某些场景下超越了人类的能力。然而，这些自动解决方案还没有准备好投入生产，因为它们很容易被简单的身份模拟攻击愚弄。尽管人们一直致力于开发人脸反欺骗模型，但其泛化能力在真实场景中仍然是一个挑战。本文介绍了一种从异常检测角度重新表述广义表示攻击检测（GPAD）问题的新方法。从技术上讲，提出了一种深度度量学习模型，将三重焦点损失作为一种新的损失的正则化，这种损失被称为“度量SoftMax”，它负责引导学习过程朝着嵌入空间中更具识别性的特征表示的方向发展。最后，我们通过引入一些后验概率估计，证明了我们的深度异常检测体系结构的好处，这种后验概率估计不需要任何分类器对所学特征进行训练。我们使用GRAD-GPAD框架进行了大量的实验，该框架为人脸GPAD提供了最大的聚合数据集。结果证实，我们的方法能够在相当大的幅度上超过所有最先进的方法。
URL
https://arxiv.org/abs/1904.08241
