Towards Maximizing the Representation Gap between In-Domain & Out-of-Distribution Examples

Part of Advances in Neural Information Processing Systems 33 (NeurIPS 2020)

AuthorFeedback »Bibtex »MetaReview »Paper »Review »Supplemental »


Jay Nandy, Wynne Hsu, Mong Li Lee


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 representation gap between in-domain and OOD examples. Experimental results demonstrate that our proposed approach consistently improves OOD detection performance.