当前位置: X-MOL 学术IEEE Trans. Multimedia › 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.)
Similarity-Aware and Variational Deep Adversarial Learning for Robust Facial Age Estimation
IEEE Transactions on Multimedia ( IF 8.4 ) Pub Date : 2020-07-01 , DOI: 10.1109/tmm.2020.2969793
Hao Liu , Penghui Sun , Jiaqiang Zhang , Suping Wu , Zhenhua Yu , Xuehong Sun

In this paper, we propose a similarity-aware deep adversarial learning (SADAL) approach for facial age estimation. Instead of making full access to the limited training samples which likely leads to bias age prediction, our SADAL aims to seek batches of unobserved hard-negative samples based on existing training samples, which typically reinforces the discriminativeness of the learned feature representation for facial ages. Motivated by the fact that age labels are usually correlated in real-world scenarios, we carefully develop a similarity-aware function to well measure the distance of each face pair based on the age value gaps. Consequently, the age-difference information is exploited in the synthetic feature space for robust age estimation. During the learning process, we jointly optimize both procedures of generating hard negatives and learning discriminative age ranker via a sequence of adversarial-game iterations. Another major issue lies on that existing methods only enforce the indiscriminativeness within each class, which is probably trapped into model overfitting and thus the generation capacity is limited particularly on unseen age classes with many individuals. To circumvent this problem, we propose a variational deep adversarial learning (VDAL) paradigm, which learns to encode each face sample in two factorized parts, i.e., the intra-class variance distribution and the intra-class invariant class center. Moreover, our VDAL principally optimizes the variational confidence lower bound on the variational factorized feature representation. To better enhance the discriminativeness of the age representation, our VDAL further learns to encode the ordinal relationship among age labels in the reconstructed subspace. Experimental results on folds of widely-evaluated benchmarking datasets demonstrate that our approach achieves promising performance in contrast to most state-of-the-art age estimation methods.

中文翻译:

用于鲁棒面部年龄估计的相似性感知和变分深度对抗学习

在本文中,我们提出了一种用于面部年龄估计的相似性感知深度对抗学习(SADAL)方法。我们的 SADAL 不是完全访问可能导致偏见年龄预测的有限训练样本,而是旨在基于现有训练样本寻找批次未观察到的硬负样本,这通常会增强所学习的面部年龄特征表示的辨别力。受年龄标签通常在现实世界场景中相关这一事实的启发,我们精心开发了一个相似性感知函数,以根据年龄值差距很好地测量每个人脸对的距离。因此,在合成特征空间中利用年​​龄差异信息进行稳健的年龄估计。在学习过程中,我们通过一系列对抗性游戏迭代来共同优化生成硬负和学习判别年龄排序的过程。另一个主要问题在于,现有方法仅在每个类中强制执行不加区分性,这可能会陷入模型过度拟合,因此生成能力有限,特别是在具有许多个体的看不见的年龄类上。为了规避这个问题,我们提出了一种变分深度对抗学习(VDAL)范式,它学习将每个人脸样本编码为两个分解部分,即类内方差分布和类内不变类中心。此外,我们的 VDAL 主要优化了变分分解特征表示的变分置信下界。为了更好地增强年龄表征的判别性,我们的 VDAL 进一步学习对重建子空间中年龄标签之间的序数关系进行编码。对广泛评估的基准数据集折叠的实验结果表明,与大多数最先进的年龄估计方法相比,我们的方法实现了有希望的性能。
更新日期:2020-07-01
down
wechat
bug