[论文] EG-ARSA: An Expert-Grounded Open Model for Visual Road Safety Auditing...

论文概要

研究领域: CV
作者: Md Thamed Bin Zaman Chowdhury, Moazzem Hossain
发布时间: 2025-08-26
arXiv: 2508.17630

中文摘要

道路交通事故是中低收入国家面临的重大挑战，但主动道路安全审计受限于不完整的事故记录、合格审计人员短缺以及大规模现场检查的高昂成本。本文提出了**Expert-Grounded Distillation (EGD)**框架，将机构道路安全专业知识迁移到紧凑的视觉-语言模型中，实现可扩展的视觉道路安全审计。核心创新是一个量化的专家锚定阶段：教师视觉-语言模型首先与权威现场审计进行校准，仅在达到与专家风险评估的实质性一致（Cohen's kappa = 0.74）后才进行大规模标注。校准后的教师生成结构化监督信号，通过LoRA和单一无泄漏提示蒸馏到80亿参数的学生模型中。本文还发布了孟加拉国首个开放、专家锚定的视觉道路安全审计数据集BD-ARSA（21,947条图像审计记录），以及专门为此任务开发的EG-ARSA模型。实验表明，锚定微调显著优于零样本基线，且紧凑学生模型在盲评中超越了310亿参数的教师和Gemini-2.5-Flash。

原文摘要

Road traffic injuries remain a major challenge in low- and middle-income countries, where proactive road safety auditing is limited by incomplete crash records, shortages of qualified auditors, and the high cost of large-scale field inspections. To address this problem, we propose Expert-Grounded Distillation (EGD), a novel artificial intelligence framework that transfers institutional road safety expertise into a compact vision-language model for scalable visual road safety auditing. The key innovation is a quantified expert-grounding stage in which the teacher vision-language model is calibrated against authoritative field audits. Large-scale annotation is permitted only after the teacher reaches substantial agreement with expert risk assessments (Cohen's kappa = 0.74). The calibrated te...

自动采集于 2026-08-26

#论文 #arXiv #CV #小凯