Generating Photo-Realistic Training Data to Improve Face Recognition Accuracy
Daniel Sáez Trigueros, Li Meng School of Engineering and Technology University of Hertfordshire Hatfield AL10 9AB, UK、Margaret Hartnett GBG plc London E14 9QD, UK
Abstract
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. Our proposed GAN allows us to augment face datasets by generating both synthetic images of subjects in the training set and synthetic images of new subjects not in the training set. By using recent advances in GAN training, we show that the synthetic images generated by our model are photo-realistic, and that training with augmented datasets can indeed increase the accuracy of face recognition models as compared with models trained with real images alone.
中文速览
用生成对抗网络（GAN）来解决人脸识别训练数据不足、分布不均衡的问题，一直是个难题，因为现有方法要么生成图像不够逼真，要么只能扩充已有人物的图片、无法凭空"创造"新身份。这篇论文提出了一种新型条件GAN，通过训练一个嵌入网络将身份标签映射到一个连续的潜空间，从而将与身份相关的特征（长相）和与身份无关的特征（姿态、光照等）彻底分离开来。基于这种解耦表示，模型既能为训练集中已有的人物生成更多样的图片（增加"深度"），也能通过随机采样身份向量来生成全新虚构人物的面孔（增加"宽度"），两个维度都能扩充数据集。实验结果表明，用真实数据加合成数据混合训练的人脸识别模型，在大多数情况下准确率都超过了纯真实数据训练的基线，证明了高质量合成人脸数据在实际工程中的可用价值。
原文 arXiv:1811.00112;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1811.00112v1