Dual Spoof Disentanglement Generation for Face Anti-spoofing with Depth Uncertainty Learning

TL;DR

This paper introduces a novel generative framework for face anti-spoofing that enhances training data diversity through disentangled face and spoofing pattern generation, and employs depth uncertainty learning to improve robustness.

Contribution

It proposes DSDG, a disentangled generative approach for diverse face spoofing data, and introduces DUM to handle noisy samples in depth estimation, advancing face anti-spoofing methods.

Findings

Achieves state-of-the-art results on five benchmarks.

Effectively improves generalization in intra- and inter-test settings.

Enhances robustness by integrating depth uncertainty learning.

Abstract

Face anti-spoofing (FAS) plays a vital role in preventing face recognition systems from presentation attacks. Existing face anti-spoofing datasets lack diversity due to the insufficient identity and insignificant variance, which limits the generalization ability of FAS model. In this paper, we propose Dual Spoof Disentanglement Generation (DSDG) framework to tackle this challenge by "anti-spoofing via generation". Depending on the interpretable factorized latent disentanglement in Variational Autoencoder (VAE), DSDG learns a joint distribution of the identity representation and the spoofing pattern representation in the latent space. Then, large-scale paired live and spoofing images can be generated from random noise to boost the diversity of the training set. However, some generated face images are partially distorted due to the inherent defect of VAE. Such noisy samples are hard to predict precise depth values, thus may obstruct the widely-used depth supervised optimization. To tackle this issue, we further introduce a lightweight Depth Uncertainty Module (DUM), which alleviates the adverse effects of noisy samples by depth uncertainty learning. DUM is developed without extra-dependency, thus can be flexibly integrated with any depth supervised network for face anti-spoofing. We evaluate the effectiveness of the proposed method on five popular benchmarks and achieve state-of-the-art results under both intra- and inter- test settings. The codes are available at https://github.com/JDAI-CV/FaceX-Zoo/tree/main/addition_module/DSDG.