{"ID":2829762,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.11373","arxiv_id":"2512.11373","title":"Out-of-Distribution Segmentation via Wasserstein-Based Evidential Uncertainty","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.","short_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...","url_abs":"https://arxiv.org/abs/2512.11373","url_pdf":"https://arxiv.org/pdf/2512.11373v1","authors":"[\"Arnold Brosch\",\"Abdelrahman Eldesokey\",\"Michael Felsberg\",\"Kira Maag\"]","published":"2025-12-12T08:36:59Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.LG\"]","methods":"[]","has_code":false}