Extraordinary progress has been made towards developing neural network architectures for classification tasks. However, commonly used loss functions such as the multi-category cross entropy loss are inadequate for ranking and ordinal regression problems. Hence, approaches that utilize neural networks for ordinal regression tasks transform ordinal target variables series of binary classification tasks but suffer from inconsistencies among the different binary classifiers. Thus, we propose a new framework (Consistent Rank Logits, CORAL) with theoretical guarantees for rank-monotonicity and consistent confidence scores. Through parameter sharing, our framework also benefits from lower training complexity and can easily be implemented to extend conventional convolutional neural network classifiers for ordinal regression tasks. Furthermore, the empirical evaluation of our method on a range of face image datasets for age prediction shows a substantial improvement compared to the current state-of-the-art ordinal regression method.
翻译:在开发用于分类任务的神经网络结构方面已经取得了非同寻常的进展,然而,通常使用的损失功能,如多类交叉环球损耗等,不足以解决排名和正反回归问题,因此,利用神经网络进行正反回归任务的方法,改变了二进制分类任务的正反目标变量系列,但不同二进制分类者之间存在不一致之处,因此,我们提出了一个新的框架(Consistent Rank Logits, CORAL),对等级-调和一致信心分数提供理论保障。通过参数共享,我们的框架还受益于较低的培训复杂性,并且可以很容易地用于扩展常规的卷态神经网络分级器,以完成正反回归任务。此外,对用于年龄预测的面图象数据集范围进行的经验评估表明,与当前最先进的正反向回归方法相比,我们的方法有了很大的改进。