Some recent work treats age estimation as an ordinal ranking task and decomposes it into multiple binary classifications. However, a theoretical defect lies in this type of methods: the ignorance of possible contradictions in individual ranking results. In this paper, we partially embrace the decomposition idea and propose the Deep and Ordinal Ensemble Learning with Two Groups Classification (DOEL _2groups ) for age prediction. An important advantage of our approach is that it theoretically allows the prediction even when the contradictory cases occur. The proposed method is characterized by a deep and ordinal ensemble and a two-stage aggregation strategy. Specifically, we first set up the ensemble based on Convolutional Neural Network (CNN) techniques, while the ordinal relationship is implicitly constructed among its base learners. Each base learner will classify the target face into one of two specific age groups. After achieving probability predictions of different age groups, then we make aggregation by transforming them into counting value distributions of whole age classes and getting the final age estimation from their votes. Moreover, to further improve the estimation performance, we suggest to regard the age class at the boundary of original two age groups as another age group and this modified version is named the Deep and Ordinal Ensemble Learning with Three Groups Classification (DOEL _3groups ). Effectiveness of this new grouping scheme is validated in theory and practice. Finally, we evaluate the proposed two ensemble methods on controlled and wild aging databases, and both of them produce competitive results. Note that the DOEL _3groups shows the state-of-the-art performance in most cases.

中文翻译：

---

基于面部图像的年龄估计的深度和顺序合奏学习

最近的一些工作将年龄估计视为序数排序任务，并将其分解为多个二进制分类。但是，这种方法存在理论上的缺陷：对单个排名结果可能存在矛盾的无知。在本文中，我们部分地接受了分解思想，并提出了具有两组分类的深度和有序集合学习（DOEL _2groups ）进行年龄预测。我们的方法的一个重要优点是，即使发生矛盾的情况，理论上它也可以进行预测。所提出的方法的特征在于深度和有序的整体以及两阶段聚合策略。具体来说，我们首先基于卷积神经网络（CNN）技术建立集合，而顺序关系是在其基础学习者之间隐式构造的。每个基础学习者都将目标面孔分类为两个特定年龄组之一。在获得不同年龄组的概率预测之后，我们通过将它们转换为整个年龄组的计数值分布并从他们的投票中获得最终年龄估算来进行汇总。此外，为了进一步提高估算性能， _3groups ）。这种新分组方案的有效性在理论和实践上得到了验证。最后，我们在受控和野生衰老数据库上评估了所提出的两种集成方法，它们都产生了竞争性结果。请注意，DOEL _3groups显示国家的最先进的性能在大多数情况下。