Face Anti-spoofing based on Multi-modal Dual-stream Anomaly Detection

Contemporary research often addresses the face anti-spoofing challenge through a classification paradigm. However, due to the rapidly changing and diverse characteristics of spoofing faces, it is unreasonable to regard all spoofing faces as a single category. Moreover, the swift evolution of spoofing techniques can render trained detectors ineffective. Anomaly detection offers a solution to these challenges by training exclusively on normal samples, distinguishing living samples as normal and non-living samples as anomalies. This paper presents a novel face anti-spoofing approach grounded in anomaly detection. It devises an RGB-D dual-stream network architecture that integrates multi-scale features from RGB and depth modalities via intermediate fusion. In addition, it also incorporates adversarial learning to facilitate network training. Furthermore, it proposes a novel multi-stage anomaly score generation technique for face anti-spoofing. Our experiments on three public datasets demonstrate the superiority of our method over comparative approaches.