论文标题
管道：用于多模式面部抗旋转的融合网络的选择性模态管道
PipeNet: Selective Modal Pipeline of Fusion Network for Multi-Modal Face Anti-Spoofing
论文作者
论文摘要
由于猖and易于发射的演示攻击，面对抗烟雾促进已成为身份验证系统越来越重要且关键的安全功能。 CASIA解决了多模式面部数据集的短缺，最近发布了最大的最新CASIA-CASIA-CASIA-SURF跨种族面对反企业（CEFA）数据集，涵盖3种族裔，3种族裔，1607个受试者，以及在四个方案中的2d加3D攻击，并挑战四个方案，并挑战了群体的挑战，并挑战了一般的通用能力，并挑战了一般的范围。连续数据。在本文中，我们提出了一种基于管道的新型多流CNN结构，称为Pipenet，用于多模式的脸部抗刺激。与以前的作品不同，选择性模态管道（SMP）旨在为每种数据模式启用定制管道，以充分利用多模式数据。有限的框架投票（LFV）旨在确保视频分类的稳定，准确的预测。提出的方法在Chalearn多模式跨种族的最终排名中赢得了第三名。我们的最终提交的平均分类错误率（ACER）为2.21，标准偏差为1.26。
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.
