This paper presents a novel perspective for enhancing anti-spoofing
performance in zero-shot data domain generalization. Unlike traditional image
classification tasks, face anti-spoofing datasets display unique generalization
characteristics, necessitating novel zero-shot data domain generalization. One
step forward to the previous frame-wise spoofing prediction, we introduce a
nuanced metric calculation that aggregates frame-level probabilities for a
video-wise prediction, to tackle the gap between the reported frame-wise
accuracy and instability in real-world use-case. This approach enables the
quantification of bias and variance in model predictions, offering a more
refined analysis of model generalization. Our investigation reveals that simply
scaling up the backbone of models does not inherently improve the mentioned
instability, leading us to propose an ensembled backbone method from a Bayesian
perspective. The probabilistically ensembled backbone both improves model
robustness measured from the proposed metric and spoofing accuracy, and also
leverages the advantages of measuring uncertainty, allowing for enhanced
sampling during training that contributes to model generalization across new
datasets. We evaluate the proposed method from the benchmark OMIC dataset and
also the public CelebA-Spoof and SiW-Mv2. Our final model outperforms existing
state-of-the-art methods across the datasets, showcasing advancements in Bias,
Variance, HTER, and AUC metrics.

本文介绍了一种增强数据域广义化中反欺骗性能的新视角，并提出了一种在视频层面上以度量为基础的方法，用于优化模型的稳定性和泛化能力。研究结果显示，简单地扩大模型的骨干网络并不能本质上改善模型的不稳定性，因此我们从贝叶斯的角度提出了一种集成骨干网络的方法，该方法在度量和欺骗准确度方面均取得了更好的结果，并能利用不确定性测量的优势，在训练过程中实现增强抽样以提升模型的泛化能力。通过在 OMC 数据集以及 CelebA-Spoof 和 SiW-Mv2 数据集上进行评估，我们的最终模型在偏差、方差、HTER 和 AUC 等指标上均超过了现有的最先进方法，展示了在这些方面的进展。