Efficient Group-n Encoding and Decoding for Facial Age Estimation
Efficient Group-n Encoding and Decoding for Facial Age Estimation
复制标题
DOI：
10.1109/tpami.2017.2779808
复制
发表时间：
2018-11
影响因子：
23.6
通讯作者：
Zichang Tan;Jun Wan;Zhen Lei;Ruicong Zhi;G. Guo;S. Li
中科院分区：
文献类型：
--
作者：
Zichang Tan;Jun Wan;Zhen Lei;Ruicong Zhi;G. Guo;S. Li
由于衰老是一个缓慢的、极不平稳的过程，具有很大的随机性，因此不同年龄之间的关系密切，尤其是相邻年龄之间的关系。为了探索真实的年龄与其相邻年龄之间的关系，提出了一种年龄组n编码（阿根）方法。在我们的模型中，相邻的年龄被分组为同一组，每个年龄对应于n组。在训练阶段，将同一年龄组的年龄视为一个独立的类别。在此基础上，将原年龄估计问题转化为一系列二元分类子问题。设计了一个具有多个分类器的深度卷积神经网络（CNN）来科普这些子问题。随后，进一步提出了局部年龄解码（LAD）策略来加速预测过程，该策略对来自有序分类器的估计年龄值进行局部解码。此外，为了减轻每个分类器的不平衡数据学习问题，惩罚因子插入到统一的目标函数，有利于少数类。为了与最先进的方法进行比较，我们在FG-NET，MORPH II，CACD和Chalearn 2015数据库上对所提出的方法进行了评估，并取得了最佳性能。
Different ages are closely related especially among the adjacent ages because aging is a slow and extremely non-stationary process with much randomness. To explore the relationship between the real age and its adjacent ages, an age group-n encoding (AGEn) method is proposed in this paper. In our model, adjacent ages are grouped into the same group and each age corresponds to n groups. The ages grouped into the same group would be regarded as an independent class in the training stage. On this basis, the original age estimation problem can be transformed into a series of binary classification sub-problems. And a deep Convolutional Neural Networks (CNN) with multiple classifiers is designed to cope with such sub-problems. Later, a Local Age Decoding (LAD) strategy is further presented to accelerate the prediction process, which locally decodes the estimated age value from ordinal classifiers. Besides, to alleviate the imbalance data learning problem of each classifier, a penalty factor is inserted into the unified objective function to favor the minority class. To compare with state-of-the-art methods, we evaluate the proposed method on FG-NET, MORPH II, CACD and Chalearn LAP 2015 databases and it achieves the best performance.