Diffusion for Out-of-Distribution Detection on Road Scenes and Beyond

Silvio Galesso, Philipp Schröppel, Hssan Driss, Thomas Brox

Abstract: In recent years, research on out-of-distribution (OoD) detection for semantic segmentation has mainly focused on road scenes – a domain with a constrained amount of semantic diversity. In this work, we challenge this constraint and extend the domain of this task to general natural images. To this end, we introduce 1. the ADE-OoD benchmark, which is based on the ADE20k dataset and includes images from diverse domains with a high semantic diversity, and 2. a novel approach that uses Diffusion score matching for OoD detection (DOoD) and is robust to the increased semantic diversity.