DEPTH-BASED ENSEMBLE LEARNING NETWORK FOR FACE ANTI-SPOOFING

Although significant progress has been made in face anti-spoofing, current methods can only achieve satisfactory results under intra-dataset settings. In other words, they tend to perform poorly when suffering from unseen attacks. Previous methods try to extract a common feature space from multiple domains, but this idea is inefficient due to the enormous distribution difference among training domains. Unlike previous methods, we assume that the data distribution of the target domain will be similar to one of the training domains. Based on this hypothesis, we draw on the idea of ensemble learning and propose a generalized framework with multiple domain-specific modules. Given a test sample, the proposed framework allows it to dynamically choose which module to use based on its similarity to the training domains. In addition, we employ GCBlock to better mine face depth information for auxiliary supervision. Since fake information is spread throughout the image, we further introduce DropBlock to avoid overfitting. Extensive experiments on four public datasets show that our approach is practical.