论文标题
通过脸部合成的异质面部识别身份 - 属性分离
Heterogeneous Face Recognition via Face Synthesis with Identity-Attribute Disentanglement
论文作者
论文摘要
异质的面部识别（HFR）旨在匹配跨不同域（例如，可见到近红外图像）的面孔，该面孔已被广泛应用于身份验证和取证方案。但是，HFR是一个具有挑战性的问题，因为跨域差异很大，异质数据对和面部属性的较大变化。为了应对这些挑战，我们从异质数据增强的角度提出了一种新的HFR方法，该方法具有身份 - 属性分解（FSIAD）的脸部合成（FSIAD）。首先，身份属性分解（IAD）将图像截取到与身份相关的表示形式和与身份无关的表示（称为属性）中，然后降低身份和属性之间的相关性。其次，我们设计一个面部合成模块（FSM），以生成大量具有分离的身份和属性的随机组合的图像，以丰富合成图像的属性多样性。原始图像和合成图像均被用于训练HFR网络，以应对挑战并提高HFR的性能。在五个HFR数据库上进行的广泛实验验证了FSIAD的性能比以前的HFR方法更高。特别是，FSIAD根据vr@far = 0.01%在LAMP-HQ上获得了4.8％的改善，这是迄今为止最大的HFR数据库。
Heterogeneous Face Recognition (HFR) aims to match faces across different domains (e.g., visible to near-infrared images), which has been widely applied in authentication and forensics scenarios. However, HFR is a challenging problem because of the large cross-domain discrepancy, limited heterogeneous data pairs, and large variation of facial attributes. To address these challenges, we propose a new HFR method from the perspective of heterogeneous data augmentation, named Face Synthesis with Identity-Attribute Disentanglement (FSIAD). Firstly, the identity-attribute disentanglement (IAD) decouples face images into identity-related representations and identity-unrelated representations (called attributes), and then decreases the correlation between identities and attributes. Secondly, we devise a face synthesis module (FSM) to generate a large number of images with stochastic combinations of disentangled identities and attributes for enriching the attribute diversity of synthetic images. Both the original images and the synthetic ones are utilized to train the HFR network for tackling the challenges and improving the performance of HFR. Extensive experiments on five HFR databases validate that FSIAD obtains superior performance than previous HFR approaches. Particularly, FSIAD obtains 4.8% improvement over state of the art in terms of VR@FAR=0.01% on LAMP-HQ, the largest HFR database so far.
