DAPONet: A Dual Attention and Partially Overparameterized Network for Real-Time Road Damage Detection
This addresses inefficient and inaccurate road damage detection for infrastructure maintenance, though it appears incremental as it builds on existing object detection methods.
The paper tackled real-time road damage detection from street view images by proposing DAPONet, which achieved a mAP50 of 70.1% on the SVRDD dataset, outperforming YOLOv10n by 10.4% while reducing parameters by 41% and FLOPs by 80%.
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.