Among existing uncertainty estimation approaches, Dirichlet Prior Network (DPN) distinctly models different predictive uncertainty types. However, for in-domain examples with high data uncertainties among multiple classes, even a DPN model often produces indistinguishable representations from the out-of-distribution (OOD) examples, compromising their OOD detection performance. We address this shortcoming by proposing a novel loss function for DPN to maximize the \textit{representation gap} between in-domain and OOD examples. Experimental results demonstrate that our proposed approach consistently improves OOD detection performance.
@article{arxiv.2010.10474,
title = {Towards Maximizing the Representation Gap between In-Domain & Out-of-Distribution Examples},
author = {Jay Nandy and Wynne Hsu and Mong Li Lee},
journal= {arXiv preprint arXiv:2010.10474},
year = {2021}
}