IEEE Trans Pattern Anal Mach Intell. 2018 Nov;40(11):2610-2623. doi: 10.1109/TPAMI.2017.2779808. Epub 2017 Dec 4.
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.
不同年龄段之间的关系非常密切，尤其是相邻年龄段之间的关系，因为衰老过程是一个缓慢且极其非平稳的过程，具有很大的随机性。为了探索真实年龄与其相邻年龄之间的关系，本文提出了一种年龄组编码（AGEn）方法。在我们的模型中，相邻的年龄被分为同一组，每个年龄对应 n 组。在训练阶段，将同一组的年龄视为一个独立的类别。在此基础上，将原始的年龄估计问题转化为一系列的二分类子问题。并设计了一个具有多个分类器的深度卷积神经网络（CNN）来处理这些子问题。随后，进一步提出了一种局部年龄解码（LAD）策略来加速预测过程，从序类器中局部解码估计的年龄值。此外，为了缓解每个分类器的不平衡数据学习问题，在统一的目标函数中插入一个惩罚因子，以支持少数类。为了与最先进的方法进行比较，我们在 FG-NET、MORPH II、CACD 和 Chalearn LAP 2015 数据库上评估了所提出的方法，取得了最佳性能。
