当前位置: X-MOL 学术ACM Trans. Multimed. Comput. Commun. Appl. › 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.)
EGroupNet
ACM Transactions on Multimedia Computing, Communications, and Applications ( IF 5.1 ) Pub Date : 2020-05-25 , DOI: 10.1145/3379449
Mingxing Duan 1 , Kenli Li 1 , Aijia Ouyang 2 , Khin Nandar Win 1 , Keqin Li 3 , Qi Tian 4
Affiliation  

Although age estimation is easily affected by smiling, race, gender, and other age-related attributes, most of the researchers did not pay attention to the correlations among these attributes. Moreover, many researchers perform age estimation from a wide range of age; however, conducting an age prediction over a narrow age range may achieve better results. This article proposes a hierarchic approach referred to as EGroupNet for age prediction. The method includes two main stages, i.e., feature enhancement via excavating the correlations among age-related attributes and age estimation based on different age group schemes. First, we apply the multi-task learning model to learn multiple face attributes simultaneously to obtain discriminative features of different attributes. Second, we project the outputs of fully connected layers of several subnetworks into a highly correlated matrix space via the correlation learning process. Third, we classify these enhanced features into narrow age groups using two Extreme Learning Machine models. Finally, we make predictions based on the results of the age groups mergence. We conduct a large number of experiments on MORPH-II, LAP-2016 dataset, and Adience benchmark. The mean absolute errors of the two different settings on MORPH-II are 2.48 and 2.13 years, respectively; the normal score (ε) on the LAP-2016 dataset is 0.3578; and the accuracy of age prediction on Adience benchmark is 0.6978.

中文翻译:

电子组网

尽管年龄估计很容易受到微笑、种族、性别和其他与年龄相关的属性的影响,但大多数研究人员并未关注这些属性之间的相关性。此外,许多研究人员从广泛的年龄范围进行年龄估计。但是,在较窄的年龄范围内进行年龄预测可能会获得更好的结果。本文提出了一种称为 EGroupNet 的分层方法,用于年龄预测。该方法包括两个主要阶段,即通过挖掘年龄相关属性之间的相关性来增强特征和基于不同年龄组方案的年龄估计。首先,我们应用多任务学习模型同时学习多个人脸属性,以获得不同属性的判别特征。第二,我们通过相关学习过程将几个子网络的完全连接层的输出投影到高度相关的矩阵空间中。第三,我们使用两个极限学习机模型将这些增强的功能分类为狭窄的年龄组。最后,我们根据年龄组合并的结果进行预测。我们在 MORPH-II、LAP-2016 数据集和 Adience 基准上进行了大量实验。MORPH-II 上两种不同设置的平均绝对误差分别为 2.48 和 2.13 年;LAP-2016 数据集上的正常分数 (ε) 为 ​​0.3578;Adience 基准上的年龄预测准确率为 0.6978。我们根据年龄组合并的结果进行预测。我们在 MORPH-II、LAP-2016 数据集和 Adience 基准上进行了大量实验。MORPH-II 上两种不同设置的平均绝对误差分别为 2.48 和 2.13 年;LAP-2016 数据集上的正常分数 (ε) 为 ​​0.3578;Adience 基准上的年龄预测准确率为 0.6978。我们根据年龄组合并的结果进行预测。我们在 MORPH-II、LAP-2016 数据集和 Adience 基准上进行了大量实验。MORPH-II 上两种不同设置的平均绝对误差分别为 2.48 和 2.13 年;LAP-2016 数据集上的正常分数 (ε) 为 ​​0.3578;Adience 基准上的年龄预测准确率为 0.6978。
更新日期:2020-05-25
down
wechat
bug