Unimodal Probability Distributions for Deep Ordinal Classification
[edit]
Proceedings of the 34th International Conference on Machine Learning, PMLR 70:411419, 2017.
Abstract
Probability distributions produced by the crossentropy 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.
Related Material


