Gradient Alignment for Cross-Domain Face Anti-Spoofing

TL;DR

This paper introduces GAC-FAS, a novel learning objective that promotes convergence to flat minima in face anti-spoofing models, enhancing cross-domain robustness without extra modules, leading to state-of-the-art results.

Contribution

GAC-FAS is a new training method that aligns gradient updates at ascending points to improve domain generalization in face anti-spoofing.

Findings

Achieves state-of-the-art cross-domain FAS performance

Effectively promotes convergence to flat minima

Enhances robustness against domain shifts

Abstract

Recent advancements in domain generalization (DG) for face anti-spoofing (FAS) have garnered considerable attention. Traditional methods have focused on designing learning objectives and additional modules to isolate domain-specific features while retaining domain-invariant characteristics in their representations. However, such approaches often lack guarantees of consistent maintenance of domain-invariant features or the complete removal of domain-specific features. Furthermore, most prior works of DG for FAS do not ensure convergence to a local flat minimum, which has been shown to be advantageous for DG. In this paper, we introduce GAC-FAS, a novel learning objective that encourages the model to converge towards an optimal flat minimum without necessitating additional learning modules. Unlike conventional sharpness-aware minimizers, GAC-FAS identifies ascending points for each domain and regulates the generalization gradient updates at these points to align coherently with empirical risk minimization (ERM) gradient updates. This unique approach specifically guides the model to be robust against domain shifts. We demonstrate the efficacy of GAC-FAS through rigorous testing on challenging cross-domain FAS datasets, where it establishes state-of-the-art performance. The code is available at https://github.com/leminhbinh0209/CVPR24-FAS.