Dual Reweighting Domain Generalization for Face Presentation Attack Detection

TL;DR

This paper introduces a Dual Reweighting Domain Generalization framework for face presentation attack detection, which iteratively adjusts sample importance and feature focus to enhance robustness against unseen scenarios.

Contribution

The proposed DRDG method innovatively combines sample and feature reweighting with a self-distilling mechanism to improve domain generalization in face anti-spoofing.

Findings

Outperforms state-of-the-art methods on multiple benchmarks.

Effectively reduces domain bias impact during training.

Enhances interpretability of the model's focus areas.

Abstract

Face anti-spoofing approaches based on domain generalization (DG) have drawn growing attention due to their robustness for unseen scenarios. Previous methods treat each sample from multiple domains indiscriminately during the training process, and endeavor to extract a common feature space to improve the generalization. However, due to complex and biased data distribution, directly treating them equally will corrupt the generalization ability. To settle the issue, we propose a novel Dual Reweighting Domain Generalization (DRDG) framework which iteratively reweights the relative importance between samples to further improve the generalization. Concretely, Sample Reweighting Module is first proposed to identify samples with relatively large domain bias, and reduce their impact on the overall optimization. Afterwards, Feature Reweighting Module is introduced to focus on these samples and extract more domain-irrelevant features via a self-distilling mechanism. Combined with the domain discriminator, the iteration of the two modules promotes the extraction of generalized features. Extensive experiments and visualizations are presented to demonstrate the effectiveness and interpretability of our method against the state-of-the-art competitors.