论文标题
基于多余的非相关学习，用于异质面部识别
Multi-Margin based Decorrelation Learning for Heterogeneous Face Recognition
论文作者
论文摘要
异构面部识别（HFR）是指从不同域中获得的匹配的面部图像在安全方案中具有广泛的应用。本文介绍了一种深神网络方法，即基于多边形的去相关学习（MMDL），以在超域面部脸部图像的超透明空间中提取去相关表示。提出的框架可以分为两个组成部分：异质表示网络和去相关表示学习。首先，我们采用大量可访问的视觉脸图像来训练异质表示网络。去相关层将第一个组件的输出投影到去相关的子空间中，并获得去相关表示。此外，我们设计了一个多修细胞损耗（MML），该损失由四局余量损耗（QML）和异质角缘损失（HAML）组成，以限制所提出的框架。两个具有挑战性的异质面部数据库的实验结果表明，与最先进的方法相比，我们的方法在验证和识别任务上都能达到卓越的性能。
Heterogeneous face recognition (HFR) refers to matching face images acquired from different domains with wide applications in security scenarios. This paper presents a deep neural network approach namely Multi-Margin based Decorrelation Learning (MMDL) to extract decorrelation representations in a hyperspherical space for cross-domain face images. The proposed framework can be divided into two components: heterogeneous representation network and decorrelation representation learning. First, we employ a large scale of accessible visual face images to train heterogeneous representation network. The decorrelation layer projects the output of the first component into decorrelation latent subspace and obtains decorrelation representation. In addition, we design a multi-margin loss (MML), which consists of quadruplet margin loss (QML) and heterogeneous angular margin loss (HAML), to constrain the proposed framework. Experimental results on two challenging heterogeneous face databases show that our approach achieves superior performance on both verification and recognition tasks, comparing with state-of-the-art methods.
