Unimodal Probability Distributions for Deep Ordinal Classification
Proceedings of the 34th International Conference on Machine Learning, PMLR 70:411-419, 2017.
Probability distributions produced by the cross-entropy loss for ordinal classification problems can possess undesired properties. We propose a straightforward technique to constrain discrete ordinal probability distributions to be unimodal via the use of the Poisson and binomial probability distributions. We evaluate this approach in the context of deep learning on two large ordinal image datasets, obtaining promising results.