Generalized Face Anti-Spoofing via Multi-Task Learning and One-Side Meta Triplet Loss

TL;DR

This paper introduces a multi-task learning framework with meta-learning and a novel triplet loss to improve face anti-spoofing, achieving better generalization across unseen domains.

Contribution

It proposes a generalized face anti-spoofing method combining depth estimation, face parsing, and classification with meta-learning and a new triplet loss for enhanced domain generalization.

Findings

Outperforms previous methods on four public datasets.

Significantly improves generalization to unseen domains.

Effective use of pixel-wise supervision and meta-learning techniques.

Abstract

With the increasing variations of face presentation attacks, model generalization becomes an essential challenge for a practical face anti-spoofing system. This paper presents a generalized face anti-spoofing framework that consists of three tasks: depth estimation, face parsing, and live/spoof classification. With the pixel-wise supervision from the face parsing and depth estimation tasks, the regularized features can better distinguish spoof faces. While simulating domain shift with meta-learning techniques, the proposed one-side triplet loss can further improve the generalization capability by a large margin. Extensive experiments on four public datasets demonstrate that the proposed framework and training strategies are more effective than previous works for model generalization to unseen domains.