发表机构
INSA Rouen Normandie; Univ Rouen Normandie; Univ Le Havre Normandie; Normandie Univ; LITIS UR 4108（鲁昂国立应用科学学院; 鲁昂大学; 勒阿弗尔大学; 诺曼底大学; 信息技术与信息系统实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出Ev-YOLO，将YOLOv8的分类与边界框回归统一纳入证据深度学习框架，在保持检测精度的同时提供可区分正确与错误检测的定位不确定性，并在领域偏移下表现更优。
AI 中文摘要
可靠的不确定性估计对于在不确定环境中运行的自主系统部署目标检测器至关重要。证据深度学习（EDL）通过将网络输出表示为证据并利用主观逻辑解释预测，为不确定性感知分类提供了一个原则性框架。然而，现有的证据目标检测器通常将证据分类与回归不确定性模型相结合，而这些模型并不共享相同的理论基础。在这项工作中，我们提出了YOLOv8的一个证据版本，其中分类和边界框回归都在一个共同的证据框架内制定。我们的方法利用了YOLOv8基于分布的边界框表示，使得证据公式不仅适用于分类，也适用于定位。因此，这两个任务都产生可以在Dempster-Shafer框架内解释的信念、不确定性和概率估计。在KITTI、MUSES和nuScenes上的实验表明，所得到的检测器在检测精度方面与标准YOLOv8大致保持竞争力，同时提供了一种能够有效区分正确和错误检测的定位不确定性。此外，在领域偏移下，这种不确定性变得越来越具有区分性。
英文摘要
Reliable uncertainty estimation is essential for deploying object detectors in autonomous systems operating in uncertain environments. Evidential Deep Learning (EDL) provides a principled framework for uncertainty-aware classification by representing network outputs as evidence and interpreting predictions through subjective logic. However, existing evidential object detectors typically combine evidential classification with regression uncertainty models that do not share the same theoretical foundation. In this work, we propose an evidential version of YOLOv8 in which both classification and bounding-box regression are formulated within a common evidential framework. Our approach exploits YOLOv8's distribution-based bounding-box representation, allowing the evidential formulation to be applied not only to classification but also to localisation. As a result, both tasks produce belief, uncertainty, and probability estimates that can be interpreted within the Dempster--Shafer framework. Experiments on KITTI, MUSES, and nuScenes show that the resulting detector remains broadly competitive with standard YOLOv8 in terms of detection accuracy while providing a localisation uncertainty that effectively discriminates between correct and erroneous detections. Moreover, this uncertainty becomes increasingly discriminative under domain shift.
CommentsPreprint / submitted manuscript. This version has not undergone peer review. To appear in the proceedings of the 9th International Conference on Belief Functions (BFAS 2026), Springer, LNAI
