Spoof Face Detection Via Semi-Supervised Adversarial Training

TL;DR

This paper introduces a semi-supervised adversarial learning framework for face spoof detection that enhances robustness and generalization by training only on live face data and using optical flow for temporal information.

Contribution

It proposes a novel semi-supervised adversarial approach that relaxes supervision requirements and improves cross-dataset robustness in face spoof detection.

Findings

Outperforms supervised methods in cross-dataset tests

Achieves comparable results to state-of-the-art techniques

Robust to unknown spoof types

Abstract

Face spoofing causes severe security threats in face recognition systems. Previous anti-spoofing works focused on supervised techniques, typically with either binary or auxiliary supervision. Most of them suffer from limited robustness and generalization, especially in the cross-dataset setting. In this paper, we propose a semi-supervised adversarial learning framework for spoof face detection, which largely relaxes the supervision condition. To capture the underlying structure of live faces data in latent representation space, we propose to train the live face data only, with a convolutional Encoder-Decoder network acting as a Generator. Meanwhile, we add a second convolutional network serving as a Discriminator. The generator and discriminator are trained by competing with each other while collaborating to understand the underlying concept in the normal class(live faces). Since the spoof face detection is video based (i.e., temporal information), we intuitively take the optical flow maps converted from consecutive video frames as input. Our approach is free of the spoof faces, thus being robust and general to different types of spoof, even unknown spoof. Extensive experiments on intra- and cross-dataset tests show that our semi-supervised method achieves better or comparable results to state-of-the-art supervised techniques.