Domain Agnostic Feature Learning for Image and Video Based Face Anti-spoofing
This addresses the need for safer user authentication in mobile and computing devices by improving generalization in face anti-spoofing, though it appears incremental as it builds on existing deep learning approaches.
The paper tackled the problem of face anti-spoofing techniques failing to generalize due to variability factors like backgrounds and lighting, and proposed a class-conditional domain discriminator with gradient reversal to generate robust features, resulting in numerical improvements over existing methods.
Nowadays, the increasingly growing number of mobile and computing devices has led to a demand for safer user authentication systems. Face anti-spoofing is a measure towards this direction for bio-metric user authentication, and in particular face recognition, that tries to prevent spoof attacks. The state-of-the-art anti-spoofing techniques leverage the ability of deep neural networks to learn discriminative features, based on cues from the training set images or video samples, in an effort to detect spoof attacks. However, due to the particular nature of the problem, i.e. large variability due to factors like different backgrounds, lighting conditions, camera resolutions, spoof materials, etc., these techniques typically fail to generalize to new samples. In this paper, we explicitly tackle this problem and propose a class-conditional domain discriminator module, that, coupled with a gradient reversal layer, tries to generate live and spoof features that are discriminative, but at the same time robust against the aforementioned variability factors. Extensive experimental analysis shows the effectiveness of the proposed method over existing image- and video-based anti-spoofing techniques, both in terms of numerical improvement as well as when visualizing the learned features.