发表机构
School of Mechanical Engineering, Zhejiang Sci-Tech University; Zhejiang Energy Digital Technology Co., Ltd; School of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics; Lingnan University（浙江理工大学机械工程学院; 浙能数字科技有限公司; 南京航空航天大学计算机科学与技术学院; 岭南大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对风机叶片缺陷检测的有限标注与弱显著性挑战，该研究提出BladeYOLO框架，通过集成改进的ViT骨干、Mamba引导增强模块等，在多个数据集上实现了更优的缺陷检测性能。
AI 中文摘要
在实际检测场景中，风机叶片缺陷检测仍极具挑战性，原因在于现场数据有限，且缺陷视觉特征微弱。实际中，叶片缺陷往往规模小、对比度低，难以与复杂背景区分，这极大限制了现有检测器的鲁棒性。为应对这些挑战，我们提出了BladeYOLO，这是一款面向风机叶片的缺陷检测框架。具体而言，我们将以DINOv3自监督预训练权重初始化的Vision Transformer（ViT）骨干网络集成到YOLOv12-L中，从而将大规模通用视觉先验迁移至叶片缺陷检测，在有限训练标注下提升特征表示能力。为增强对细微缺陷的感知，我们进一步开发了Mamba引导的弱缺陷增强模块，该模块包含用于保留高频结构线索的细节增强多尺度分支，以及用于将高层语义引导逐步传播至浅层特征的Cross-Mamba模块。此外，我们引入了轻量型Style-Injector模块，该模块通过傅里叶分解捕获与环境相关的风格信息，并将其注入选定的ViT自注意力层，从而提升对环境诱导外观变化的鲁棒性。大量实验表明，BladeYOLO在WTBlade-Defect数据集上实现了优异性能；额外的标注预算实验显示，其在减少训练标注时仍表现良好。在公开的Wind Surface Defect数据集上的评估进一步为BladeYOLO的跨数据集鲁棒性提供了支撑证据。尤其在该公开数据集上，BladeYOLO的mAP₅₀较最优对比方法高出3.5%，mAP₅₀-₉₅则高出2.5%。
英文摘要
Wind turbine blade defect detection remains highly challenging in real-world inspection scenarios due to limited on-site data and the subtle visual characteristics of defects. In practice, blade defects are often small-scale, low-contrast, and difficult to distinguish from complex backgrounds, which significantly limits the robustness of existing detectors. To address these challenges, we propose BladeYOLO, a defect detection framework for wind turbine blades. Specifically, we integrate a Vision Transformer (ViT) backbone initialized with DINOv3 self-supervised pre-trained weights into YOLOv12-L, enabling the transfer of large-scale generic visual priors to blade defect detection and improving feature representation under limited training annotations. To enhance the perception of subtle defects, we further develop a Mamba-guided Weak-Defect Enhancement module, which consists of a Detail-Enhanced Multi-scale Branch for preserving high-frequency structural cues and a Cross-Mamba module for progressively propagating high-level semantic guidance to shallow features. In addition, we introduce a lightweight Style-Injector module that captures environment-related style information via Fourier decomposition and injects it into selected ViT self-attention layers, thereby improving robustness against environment-induced appearance variations. Extensive experiments demonstrate that BladeYOLO achieves superior performance on the WTBlade-Defect dataset, with additional annotation-budget experiments showing its favorable performance under reduced training annotations. Evaluation on the public Wind Surface Defect dataset further provides supportive evidence for the cross-dataset robustness of BladeYOLO. In particular, on this public dataset, BladeYOLO outperforms the best competing method by 3.5\% in mAP$_{50}$ and 2.5\% in mAP$_{50-95}$.
CommentsAccepted to IEEE TGRS, Code: https://github.com/zhangfangtao/BladeYOLO
