Generalized Face Anti-spoofing via Finer Domain Partition and Disentangling Liveness-irrelevant Factors

TL;DR

This paper proposes a novel face anti-spoofing method that redefines domains by identities, disentangles liveness from identity features, and employs style augmentation and contrastive loss to improve cross-dataset robustness.

Contribution

It introduces identity-based domain partitioning, orthogonal liveness-identity feature learning, style augmentation modules, and a new contrastive loss for enhanced generalization in face anti-spoofing.

Findings

Achieves state-of-the-art results on four public datasets.

Demonstrates robustness in cross-dataset and limited data scenarios.

Shows scalability with increased identity diversity.

Abstract

Face anti-spoofing techniques based on domain generalization have recently been studied widely. Adversarial learning and meta-learning techniques have been adopted to learn domain-invariant representations. However, prior approaches often consider the dataset gap as the primary factor behind domain shifts. This perspective is not fine-grained enough to reflect the intrinsic gap among the data accurately. In our work, we redefine domains based on identities rather than datasets, aiming to disentangle liveness and identity attributes. We emphasize ignoring the adverse effect of identity shift, focusing on learning identity-invariant liveness representations through orthogonalizing liveness and identity features. To cope with style shifts, we propose Style Cross module to expand the stylistic diversity and Channel-wise Style Attention module to weaken the sensitivity to style shifts, aiming to learn robust liveness representations. Furthermore, acknowledging the asymmetry between live and spoof samples, we introduce a novel contrastive loss, Asymmetric Augmented Instance Contrast. Extensive experiments on four public datasets demonstrate that our method achieves state-of-the-art performance under cross-dataset and limited source dataset scenarios. Additionally, our method has good scalability when expanding diversity of identities. The codes will be released soon.