TeG-DG: Textually Guided Domain Generalization for Face Anti-Spoofing

TL;DR

This paper introduces TeG-DG, a novel framework that uses text information to improve domain generalization in face anti-spoofing, especially effective with limited training data.

Contribution

It proposes a textually guided domain generalization framework with a Hierarchical Attention Fusion module and a Textual-Enhanced Visual Discriminator for better cross-domain alignment.

Findings

Significantly outperforms previous methods in limited data scenarios.

Achieves approximately 14% and 12% improvements on HTER and AUC.

Demonstrates strong few-shot domain generalization capabilities.

Abstract

Enhancing the domain generalization performance of Face Anti-Spoofing (FAS) techniques has emerged as a research focus. Existing methods are dedicated to extracting domain-invariant features from various training domains. Despite the promising performance, the extracted features inevitably contain residual style feature bias (e.g., illumination, capture device), resulting in inferior generalization performance. In this paper, we propose an alternative and effective solution, the Textually Guided Domain Generalization (TeG-DG) framework, which can effectively leverage text information for cross-domain alignment. Our core insight is that text, as a more abstract and universal form of expression, can capture the commonalities and essential characteristics across various attacks, bridging the gap between different image domains. Contrary to existing vision-language models, the proposed framework is elaborately designed to enhance the domain generalization ability of the FAS task. Concretely, we first design a Hierarchical Attention Fusion (HAF) module to enable adaptive aggregation of visual features at different levels; Then, a Textual-Enhanced Visual Discriminator (TEVD) is proposed for not only better alignment between the two modalities but also to regularize the classifier with unbiased text features. TeG-DG significantly outperforms previous approaches, especially in situations with extremely limited source domain data (~14% and ~12% improvements on HTER and AUC respectively), showcasing impressive few-shot performance.