Scholarlink

<p>Vehicle detection in adverse weather is crucial for autonomous driving; however, fog, rain, snow, and low illumination significantly degrade feature quality and detection reliability. This paper presents YOLOv8s-WAMNet (weather-adaptive multi-scale network), a lightweight hybrid attention framework designed to maintain robustness under visibility degradation. The model employs an efficient hybrid vision transformer backbone that combines convolutional and transformer-based feature extraction for resilient representation learning. Cross-dimensional multi-scale attention and a contextual multi-attention fusion neck enhance multi-scale feature refinement and stabilize spatial–contextual reasoning in adverse scenes. A multi-head dynamic attention detection head with a hybrid SIoU–MPDIoU loss further improves localization accuracy and convergence stability. Extensive experiments on the WEather images by DALL-E GEneration dataset demonstrate that YOLOv8s-WAMNet achieves <InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(51.90\%\)</EquationSource> </InlineEquation> mAP@50 and <InlineEquation ID="IEq2"> <EquationSource Format="TEX">\(24.96\%\)</EquationSource> </InlineEquation> mAP@50–95, outperforming YOLOv8s by <InlineEquation ID="IEq3"> <EquationSource Format="TEX">\(+6.3\)</EquationSource> </InlineEquation> mAP@50 while reducing computational cost by approximately <InlineEquation ID="IEq4"> <EquationSource Format="TEX">\(54\%\)</EquationSource> </InlineEquation> (13.24 vs. 28.7 GFLOPs). Additional evaluations on the real-world detection in adverse weather nature dataset confirm the robustness and cross-dataset generalization capability of the proposed model.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

YOLOv8s-WAMNet: enhancing robust vehicle detection under adverse weather via hybrid attention and multi-scale fusion in real time

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年4月3日

查看全文
  • Manjit Jaiswal,
  • Kapil Kumar Nagwanshi,
  • Maleika Heenaye-Mamode Khan,
  • Upendra Verma,
  • Amelia Taylor

摘要

Vehicle detection in adverse weather is crucial for autonomous driving; however, fog, rain, snow, and low illumination significantly degrade feature quality and detection reliability. This paper presents YOLOv8s-WAMNet (weather-adaptive multi-scale network), a lightweight hybrid attention framework designed to maintain robustness under visibility degradation. The model employs an efficient hybrid vision transformer backbone that combines convolutional and transformer-based feature extraction for resilient representation learning. Cross-dimensional multi-scale attention and a contextual multi-attention fusion neck enhance multi-scale feature refinement and stabilize spatial–contextual reasoning in adverse scenes. A multi-head dynamic attention detection head with a hybrid SIoU–MPDIoU loss further improves localization accuracy and convergence stability. Extensive experiments on the WEather images by DALL-E GEneration dataset demonstrate that YOLOv8s-WAMNet achieves \(51.90\%\) mAP@50 and \(24.96\%\) mAP@50–95, outperforming YOLOv8s by \(+6.3\) mAP@50 while reducing computational cost by approximately \(54\%\) (13.24 vs. 28.7 GFLOPs). Additional evaluations on the real-world detection in adverse weather nature dataset confirm the robustness and cross-dataset generalization capability of the proposed model.