结合自监督学习和生成对抗网络的小样本人脸属性识别  

Self-supervised learning and generative adversarial network-based facial attribute recognition with small sample size training

作　　者：疏颖 毛龙彪 陈思 严严[1,2] Shu Ying;Mao Longbiao;Chen Si;Yan Yan(School of Informatics,Xiamen University,Xiamen 361005,China;Fujian Key Laboratory of Sensing and Computing for Smart City,Xiamen University,Xiamen 361005,China;School of Computer and Information Engineering,Xiamen University of Technology,Xiamen 361024,China)

机构地区：[1]厦门大学信息学院,厦门361005 [2]厦门大学福建省智慧城市感知与计算重点实验室,厦门361005 [3]厦门理工学院计算机与信息工程学院,厦门361024

出　　处：《中国图象图形学报》2020年第11期2391-2403,共13页Journal of Image and Graphics

基　　金：国家自然科学基金项目(62071404,U1605252,61872307);国家重点研发计划项目(2017YFB1302400)。

摘　　要：目的人脸属性识别是计算机视觉和情感感知等领域一个重要的研究课题。随着深度学习的不断发展,人脸属性识别取得了巨大的进步。目前基于深度学习的人脸属性识别方法大多依赖于包含完整属性标签信息的大规模数据集。然而,对于小样本数据集的属性标签缺失问题,人脸属性识别方法的准确率依然较低。针对上述问题,本文提出了一种结合自监督学习和生成对抗网络的方法来提高在小样本数据集上的人脸属性识别准确率。方法使用基于旋转的自监督学习技术进行预训练得到初始的属性识别网络;使用基于注意力机制的生成对抗网络得到人脸属性合成模型,对人脸图像进行属性编辑从而扩充训练数据集;使用扩充后的训练数据集对属性识别网络进行训练得到最终模型。结果本文在小样本数据集UMD-AED(University of Maryland attribute evaluation dataset)上进行了实验并与传统的有监督学习方法进行了比较。传统的有监督学习方法达到了63.24%的平均准确率,而所提方法达到了69.01%的平均准确率,提高了5.77%。同时,本文在Celeb A(Celeb Faces attributes dataset)、LFWA(labeled faces in the wild attributes dataset)和UMD-AED数据集上进行了使用自监督学习和未使用自监督学习的对比实验,验证了自监督学习在小样本数据集上的有效性。结论本文所提出的结合自监督学习和生成对抗网络的人脸属性识别方法有效提高了小样本数据集上属性识别的准确率。Objective Facial attribute recognition is an important research topic in the fields of computer vision and emotion sensing.Face,an important biological feature of human beings,contains a large number of attributes,such as expression,age,and gender.Facial attribute recognition aims to predict the different attributes in a given facial image.Facial attribute recognition has progressed considerably with the remarkable development of deep learning.State-of-the-art deep learningbased facial attribute recognition methods typically rely on large-scale training facial data with complete attribute labels.However,the number of training facial data may be limited in some real-world applications and several attribute labels of the facial image are unavailable,mainly because attribute labeling is a time-consuming and labor-intensive task.Notably,defining a standard criterion for attribute labeling is difficult for some subjective attributes.As a result,the accuracy of these methods is poor when addressing the problem of missing attribute labels in small sample size training.Previous methods attempted to find samples that match the required label from the unlabeled dataset and then added these samples to the corresponding category of the training set to augment the training data.Note that the unlabeled dataset is typically of low quality,thereby affecting the final performance of the model.Furthermore,the selection of matching samples is time consuming.Some methods directly take advantage of similar data to augment the original dataset.However,deciding whether two datasets are similar and finding similar datasets are still challenging.Current methods need further investigation on facial attribute recognition under small sample size training.A self-supervised learning and generative adversarial network(GAN)-based method is proposed in this study to solve the above-mentioned problems and improve the accuracy of facial attribute recognition for small sample size training with missing attribute labels.Method First,we adopt a rotat

关 键 词：人脸属性识别 自监督学习 生成对抗网络(GAN) 数据增强 小样本训练 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]