Ev-YOLO: Uncertainty-Aware Object Detection via a Unified Evidential Formulation

2026-09-21

AI Summary

本文提出了一种基于证据理论的YOLOv8版本（Ev-YOLO），通过统一的证据框架处理分类和边界框回归任务，以提高在不确定环境下的物体检测可靠性。

Abstract

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.

Problem

• Uncertainty Estimation
• Object Detection
• Evidential Deep Learning
• Autonomous Systems

Innovation

• Evidential Deep Learning
• Uncertainty-Aware Object Detection
• Unified Evidential Framework
• Dempster--Shafer Theory