Face recognition has become a widely adopted biometric in forensics, security and law enforcement thanks to the high accuracy achieved by systems based on convolutional neural networks (CNNs). However, to achieve good performance, CNNs need to be trained with very large datasets which are not always available. In this paper we investigate the feasibility of using synthetic data to augment face datasets. In particular, we propose a novel generative adversarial network (GAN) that can disentangle identity-related attributes from non-identity-related attributes. This is done by training an embedding network that maps discrete identity labels to an identity latent space that follows a simple prior distribution, and training a GAN conditioned on samples from that distribution. A main novelty of our approach is the ability to generate both synthetic images of subjects in the training set and synthetic images of new subjects not in the training set, both of which we use to augment face datasets. By using recent advances in GAN training, we show that the synthetic images generated by our model are photo-realistic, and that training with datasets augmented with those images can lead to increased recognition accuracy. Experimental results show that our method is more effective when augmenting small datasets. In particular, an absolute accuracy improvement of 8.42% was achieved when augmenting a dataset of less than 60k facial images.

由于基于卷积神经网络（CNN）的系统具有很高的准确性，因此面部识别已成为取证，安全和执法领域广泛采用的生物识别技术。但是，为了获得良好的性能，CNN需要使用非常大的数据集进行训练，而这些数据集并不总是可用。在本文中，我们研究了使用合成数据来扩充人脸数据集的可行性。特别是，我们提出了一种新颖的生成对抗网络（GAN），可以将身份相关属性与非身份相关属性区分开。这是通过训练将离散身份标识映射到遵循简单先验分布的潜在身份空间的嵌入网络，并训练基于该分布样本的GAN来完成的。我们方法的主要新颖之处在于既可以生成训练集中的主题的合成图像，又可以生成不在训练集中的新主题的合成图像，我们都使用这两种图像来增强人脸数据集。通过使用GAN训练的最新进展，我们证明了由我们的模型生成的合成图像具有照片级逼真的效果，并且使用带有这些图像的数据集进行训练可以提高识别精度。实验结果表明，该方法在扩充小型数据集时更为有效。特别是，当扩充少于60k人脸图像的数据集时，绝对精度提高了8.42％。我们表明，由我们的模型生成的合成图像具有照片级逼真的效果，并且使用这些图像扩充的数据集进行训练可以提高识别精度。实验结果表明，该方法在扩充小型数据集时更为有效。特别是，当扩充少于60k人脸图像的数据集时，绝对精度提高了8.42％。我们表明，由我们的模型生成的合成图像具有照片级逼真的效果，并且使用这些图像扩充的数据集进行训练可以提高识别精度。实验结果表明，该方法在扩充小型数据集时更为有效。特别是，当扩充少于60k人脸图像的数据集时，绝对精度提高了8.42％。