Style-Guided Domain Adaptation for Face Presentation Attack Detection

TL;DR

This paper introduces a novel style-guided domain adaptation framework for face presentation attack detection that enhances robustness against unseen attack scenarios by leveraging style-specific information during inference.

Contribution

It proposes Style-Selective Normalization and Style-Aware Meta-Learning to improve domain adaptation without needing auxiliary models or unlabeled target data during training.

Findings

Significant performance improvements over existing DA/DG PAD methods.

Effective adaptation to unseen attack styles in various datasets.

No need for auxiliary models or unlabeled target data during training.

Abstract

Domain adaptation (DA) or domain generalization (DG) for face presentation attack detection (PAD) has attracted attention recently with its robustness against unseen attack scenarios. Existing DA/DG-based PAD methods, however, have not yet fully explored the domain-specific style information that can provide knowledge regarding attack styles (e.g., materials, background, illumination and resolution). In this paper, we introduce a novel Style-Guided Domain Adaptation (SGDA) framework for inference-time adaptive PAD. Specifically, Style-Selective Normalization (SSN) is proposed to explore the domain-specific style information within the high-order feature statistics. The proposed SSN enables the adaptation of the model to the target domain by reducing the style difference between the target and the source domains. Moreover, we carefully design Style-Aware Meta-Learning (SAML) to boost the adaptation ability, which simulates the inference-time adaptation with style selection process on virtual test domain. In contrast to previous domain adaptation approaches, our method does not require either additional auxiliary models (e.g., domain adaptors) or the unlabeled target domain during training, which makes our method more practical to PAD task. To verify our experiments, we utilize the public datasets: MSU-MFSD, CASIA-FASD, OULU-NPU and Idiap REPLAYATTACK. In most assessments, the result demonstrates a notable gap of performance compared to the conventional DA/DG-based PAD methods.