English

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

Machine Learning 2021-01-07 v2 Artificial Intelligence

Abstract

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.

Keywords

Cite

@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}
}

Comments

Accepted at NeurIPS 2020 Workshop version: ICML UDL 2020, Link: http://www.gatsby.ucl.ac.uk/~balaji/udl2020/accepted-papers/UDL2020-paper-134.pdf

R2 v1 2026-06-23T19:29:50.910Z