Neural networks deployed in high-stakes scenarios need to provide inference that is robust to out-of-distribution (OOD) inputs. Although the resilience of neural networks to such inputs has been widely investigated in the uncertainty estimation and OOD detection communities, a unified vision of these inherently intertwined problem domains is still missing. In this work, we fill this gap by providing a survey of the state of the art that brings together research on both uncertainty estimation and OOD detection, ultimately offering a consolidated view of methods, tools, and benchmarks. We categorize existing OOD techniques by the task they address (multi-class and multi-label classification, segmentation, object detection), thus exposing progress and remaining challenges beyond the usual multi-class setting. Moreover, we highlight emerging themes such as test-time adaptation for OOD detection and new theoretical results that probe its fundamental limits, thereby outlining promising and under-explored directions for future research.
Sayyed et al. (Wed,) studied this question.