PipeNet: Selective Modal Pipeline of Fusion Network for Multi-Modal Face Anti-Spoofing

TL;DR

This paper introduces PipeNet, a multi-modal face anti-spoofing network with a selective pipeline for each modality, achieving high accuracy and stability on a challenging dataset, and securing third place in a CVPR challenge.

Contribution

The paper proposes a novel multi-stream CNN architecture with selective modality pipelines and limited frame voting for improved multi-modal face anti-spoofing.

Findings

Achieved an ACER of 2.21 on the test set.

Secured third place in the CVPR2020 challenge.

Demonstrated improved generalization on multi-modal data.

Abstract

Face anti-spoofing has become an increasingly important and critical security feature for authentication systems, due to rampant and easily launchable presentation attacks. Addressing the shortage of multi-modal face dataset, CASIA recently released the largest up-to-date CASIA-SURF Cross-ethnicity Face Anti-spoofing(CeFA) dataset, covering 3 ethnicities, 3 modalities, 1607 subjects, and 2D plus 3D attack types in four protocols, and focusing on the challenge of improving the generalization capability of face anti-spoofing in cross-ethnicity and multi-modal continuous data. In this paper, we propose a novel pipeline-based multi-stream CNN architecture called PipeNet for multi-modal face anti-spoofing. Unlike previous works, Selective Modal Pipeline (SMP) is designed to enable a customized pipeline for each data modality to take full advantage of multi-modal data. Limited Frame Vote (LFV) is designed to ensure stable and accurate prediction for video classification. The proposed method wins the third place in the final ranking of Chalearn Multi-modal Cross-ethnicity Face Anti-spoofing Recognition Challenge@CVPR2020. Our final submission achieves the Average Classification Error Rate (ACER) of 2.21 with Standard Deviation of 1.26 on the test set.