BladeYOLO: Wind Turbine Blade Defect Detection With Limited Annotations and Weak-Saliency Awareness
This work proposes BladeYOLO, a defect detection framework for wind turbine blades that achieves superior performance on the WTBlade-Defect dataset, and introduces a lightweight style-injector module that captures environment-related style information via Fourier decomposition and injects it into selected ViT self-atte...