Learning Polysemantic Spoof Trace: A Multi-Modal Disentanglement Network for Face Anti-spoofing

TL;DR

This paper introduces a multi-modal disentanglement network that leverages RGB and depth data to improve face anti-spoofing by capturing diverse spoof traces, enhancing robustness and interpretability across various attack scenarios.

Contribution

It proposes a novel multi-modal adversarial framework for disentangling polysemantic spoof traces, significantly advancing face anti-spoofing accuracy and generalization.

Findings

Outperforms existing methods on multiple benchmarks

Effectively captures complementary spoof clues from RGB and depth

Provides more interpretable spoof trace representations

Abstract

Along with the widespread use of face recognition systems, their vulnerability has become highlighted. While existing face anti-spoofing methods can be generalized between attack types, generic solutions are still challenging due to the diversity of spoof characteristics. Recently, the spoof trace disentanglement framework has shown great potential for coping with both seen and unseen spoof scenarios, but the performance is largely restricted by the single-modal input. This paper focuses on this issue and presents a multi-modal disentanglement model which targetedly learns polysemantic spoof traces for more accurate and robust generic attack detection. In particular, based on the adversarial learning mechanism, a two-stream disentangling network is designed to estimate spoof patterns from the RGB and depth inputs, respectively. In this case, it captures complementary spoofing clues inhering in different attacks. Furthermore, a fusion module is exploited, which recalibrates both representations at multiple stages to promote the disentanglement in each individual modality. It then performs cross-modality aggregation to deliver a more comprehensive spoof trace representation for prediction. Extensive evaluations are conducted on multiple benchmarks, demonstrating that learning polysemantic spoof traces favorably contributes to anti-spoofing with more perceptible and interpretable results.