In many real-world prediction tasks, class labels include information about the relative ordering between labels, which is not captured by commonly-used loss functions such as multi-category cross-entropy. Recently, the deep learning community adopted ordinal regression frameworks to take such ordering information into account. Neural networks were equipped with ordinal regression capabilities by transforming ordinal targets into binary classification subtasks. However, this method suffers from inconsistencies among the different binary classifiers. To resolve these inconsistencies, we propose the COnsistent RAnk Logits (CORAL) framework with strong theoretical guarantees for rank-monotonicity and consistent confidence scores. Moreover, the proposed method is architecture-agnostic and can extend arbitrary state-of-the-art deep neural network classifiers for ordinal regression tasks. The empirical evaluation of the proposed rank-consistent method on a range of face-image datasets for age prediction shows a substantial reduction of the prediction error compared to the reference ordinal regression network.

在许多现实世界的预测任务中，类别标签包含有关标签之间相对顺序的信息，而这些信息却无法通过常用的损失函数（如多类别交叉熵）捕获。最近，深度学习社区采用了序数回归框架来考虑此类排序信息。通过将有序目标转化为二元分类子任务，神经网络具备了有序回归功能。然而，该方法遭受不同二进制分类器之间的不一致的困扰。为了解决这些不一致的问题，我们提出了一致的等级逻辑（CORAL）框架，该框架为等级单调性和一致的置信度得分提供了有力的理论保证。此外，所提出的方法与体系结构无关，并且可以扩展用于序数回归任务的任意最新的深度神经网络分类器。对用于年龄预测的一系列面部图像数据集所提出的等级一致方法的经验评估表明，与参考序数回归网络相比，预测误差显着降低。