# Deep Anomaly Detection for Generalized Face Anti-Spoofing

## TL;DR

This paper presents a deep anomaly detection approach for face anti-spoofing that improves generalization and outperforms state-of-the-art methods by using a novel loss function and few-shot probability estimation.

## Contribution

It introduces a deep metric learning model with a new metric-softmax loss and a few-shot probability estimation for generalized face anti-spoofing.

## Key findings

- Outperforms all state-of-the-art methods on GRAD-GPAD dataset
- Uses a triplet focal loss with a novel metric-softmax loss for discriminative features
- Demonstrates effectiveness in few-shot a posteriori probability estimation

## Abstract

Face recognition has achieved unprecedented results, surpassing human capabilities in certain scenarios. However, these automatic solutions are not ready for production because they can be easily fooled by simple identity impersonation attacks. And although much effort has been devoted to develop face anti-spoofing models, their generalization capacity still remains a challenge in real scenarios. In this paper, we introduce a novel approach that reformulates the Generalized Presentation Attack Detection (GPAD) problem from an anomaly detection perspective. Technically, a deep metric learning model is proposed, where a triplet focal loss is used as a regularization for a novel loss coined "metric-softmax", which is in charge of guiding the learning process towards more discriminative feature representations in an embedding space. Finally, we demonstrate the benefits of our deep anomaly detection architecture, by introducing a few-shot a posteriori probability estimation that does not need any classifier to be trained on the learned features. We conduct extensive experiments using the GRAD-GPAD framework that provides the largest aggregated dataset for face GPAD. Results confirm that our approach is able to outperform all the state-of-the-art methods by a considerable margin.