DAPONet提升街景图像中道路损伤实时检测精度与效率
DAPONet: A Dual Attention and Partially Overparameterized Network for Real-Time Road Damage Detection
- 融合全局与局部注意力，增强特征表达能力
- 在SVRDD上达到70.1% mAP50，比YOLOv10n高10.4%
- 模型参数仅160万，计算量降低80%，适合边缘部署
现有道路损伤检测方法依赖人工巡查或车载传感器，效率低、覆盖有限且对细微损伤识别不准，易引发延误与安全隐患。为提升基于街景图像数据（SVRDD）的实时道路损伤检测性能，本文提出DAPONet，包含三个核心模块：双注意力机制（融合全局与局部注意力）、多尺度部分过参数化模块和高效下采样模块。在SVRDD数据集上，DAPONet取得70.1%的mAP50，较YOLOv10n提升10.4%，参数量降至1.6M，计算量（FLOPs）降至1.7G，分别减少41%和80%。在MS COCO2017 val数据集上，mAP50-95达33.4%，较EfficientDet-D1高0.8%，参数与计算量均减少74%。
原文摘要 · Abstract (English)
Current road damage detection methods, relying on manual inspections or sensor-mounted vehicles, are inefficient, limited in coverage, and often inaccurate, especially for minor damages, leading to delays and safety hazards. To address these issues and enhance real-time road damage detection using street view image data (SVRDD), we propose DAPONet, a model incorporating three key modules: a dual attention mechanism combining global and local attention, a multi-scale partial over-parameterization module, and an efficient downsampling module. DAPONet achieves a mAP50 of 70.1% on the SVRDD dataset, outperforming YOLOv10n by 10.4%, while reducing parameters to 1.6M and FLOPs to 1.7G, representing reductions of 41% and 80%, respectively. On the MS COCO2017 val dataset, DAPONet achieves an mAP50-95 of 33.4%, 0.8% higher than EfficientDet-D1, with a 74% reduction in both parameters and FLOPs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。