当前位置: X-MOL 学术IEEE Trans. Inform. Forensics Secur. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Facial Age and Expression Synthesis Using Ordinal Ranking Adversarial Networks
IEEE Transactions on Information Forensics and Security ( IF 6.3 ) Pub Date : 3-17-2020 , DOI: 10.1109/tifs.2020.2980792
Yunlian Sun , Jinhui Tang , Zhenan Sun , Massimo Tistarelli

Facial image synthesis has been extensively studied, for a long time, in both computer graphics and computer vision. Particularly, the synthesis of face images with varying ages, expressions and poses has received an increasing attention owing to several real-world applications. In this paper, facial age and expression synthesis are addressed. While previous and current research papers on facial age synthesis mostly adopt an age span of 10 years, this paper investigates face aging with a shorter time span. For expression synthesis, given a neutral face, we work on synthesizing faces with varying expression intensities (e.g., from zero to high). Note that both human ages and expression intensities are inherently ordinal. To fully exploit this ordinal nature, we devise ordinal ranking generative adversarial networks (ranking GAN). For each face, a one-hot label is assigned to define its age range/expression intensity. By exploiting the relative order information among age ranges/expression intensities, a binary ranking vector is further computed for each face. In ranking GAN, one-hot labels are used as the condition of the generator for synthesizing faces with target age groups/expression intensities. Moreover, we add a sequence of cost-sensitive ordinal rankers on top of several multi-scale discriminators, with the aim of minimizing age/intensity rank estimation loss when optimizing both the generator and discriminators. In order to evaluate the proposed ranking GAN, extensive experiments are carried out on several public face databases. As demonstrated by the experimental testing, this ranking scheme performs well even when the amount of available labeled training data is limited. The reported experimental results well demonstrate the effectiveness of ranking GAN on synthesizing face aging sequences and faces with varying expression intensities.

中文翻译:


使用序数排名对抗网络进行面部年龄和表情合成



长期以来,面部图像合成在计算机图形学和计算机视觉领域得到了广泛的研究。特别是,由于一些实际应用,不同年龄、表情和姿势的人脸图像的合成受到越来越多的关注。在本文中,讨论了面部年龄和表情合成。虽然之前和当前关于面部年龄综合的研究论文大多采用10年的年龄跨度,但本文研究了更短时间跨度的面部衰老。对于表情合成,给定一个中性面孔,我们致力于合成具有不同表情强度(例如,从零到高)的面孔。请注意,人类年龄和表达强度本质上都是有序的。为了充分利用这种序数性质,我们设计了序数排名生成对抗网络(排名 GAN)。对于每一张脸,都会分配一个单热标签来定义其年龄范围/表情强度。通过利用年龄范围/表情强度之间的相对顺序信息,进一步计算每张脸的二元排名向量。在排序 GAN 中,使用 one-hot 标签作为生成器的条件,用于合成具有目标年龄组/表情强度的人脸。此外,我们在几个多尺度鉴别器之上添加了一系列成本敏感的序数排名器,目的是在优化生成器和鉴别器时最小化年龄/强度排名估计损失。为了评估所提出的排名 GAN,在几个公共人脸数据库上进行了广泛的实验。正如实验测试所证明的,即使可用的标记训练数据量有限,这种排序方案也表现良好。 报道的实验结果很好地证明了对 GAN 进行排序在合成人脸衰老序列和不同表情强度的人脸方面的有效性。
更新日期:2024-08-22
down
wechat
bug