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 t
本文提出了一种基于 Correctness Ranking Loss 的深度神经网络训练方法，可以对类别概率进行显式的正序排名，提高置信度预测。该方法易于实现，不需要额外的计算代价，适用于现有体系结构，并且在分类基准数据集上表现良好。同时，还对置信度估计相关的任务，如超出分布检测和主动学习，具有相同的可靠性。