Learning Generalizable and Identity-Discriminative Representations for Face Anti-Spoofing

TL;DR

This paper introduces GFA-CNN, a face anti-spoofing model that improves generalization across unseen domains by using a novel Total Pairwise Confusion loss and Fast Domain Adaptation, while also maintaining face recognition capabilities.

Contribution

The paper proposes a new CNN model with Total Pairwise Confusion loss and Fast Domain Adaptation to enhance generalizability and domain robustness in face anti-spoofing, while enabling multi-task face recognition.

Findings

GFA-CNN outperforms previous anti-spoofing methods.

The model maintains identity information effectively.

Enhanced robustness to unseen domain variations.

Abstract

Face anti-spoofing (a.k.a presentation attack detection) has drawn growing attention due to the high-security demand in face authentication systems. Existing CNN-based approaches usually well recognize the spoofing faces when training and testing spoofing samples display similar patterns, but their performance would drop drastically on testing spoofing faces of unseen scenes. In this paper, we try to boost the generalizability and applicability of these methods by designing a CNN model with two major novelties. First, we propose a simple yet effective Total Pairwise Confusion (TPC) loss for CNN training, which enhances the generalizability of the learned Presentation Attack (PA) representations. Secondly, we incorporate a Fast Domain Adaptation (FDA) component into the CNN model to alleviate negative effects brought by domain changes. Besides, our proposed model, which is named Generalizable Face Authentication CNN (GFA-CNN), works in a multi-task manner, performing face anti-spoofing and face recognition simultaneously. Experimental results show that GFA-CNN outperforms previous face anti-spoofing approaches and also well preserves the identity information of input face images.