# Out-of-Distribution Segmentation via Wasserstein-Based Evidential Uncertainty Source: [Out-of-Distribution Segmentation via Wasserstein-Based Evidential Uncertainty]() Collection index: [llms.txt]() Data updated: 2025-12-16T05:00:10.037Z Authors: Arnold Brosch, Abdelrahman Eldesokey, Michael Felsberg, Kira Maag Published: 2025-12-12T08:36:59.000Z ## Abstract Deep neural networks achieve superior performance in semantic segmentation, but are limited to a predefined set of classes, which leads to failures when they encounter unknown objects in open-world scenarios. Recognizing and segmenting these out-of-distribution (OOD) objects is crucial for safety-critical applications such as automated driving. In this work, we present an evidence segmentation framework using a Wasserstein loss, which captures distributional distances while respecting the probability simplex geometry. Combined with Kullback-Leibler regularization and Dice structural consistency terms, our approach leads to improved OOD segmentation performance compared to uncertainty-based approaches. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()