A Mix Transformer–Enhanced UNet for Concrete Building Surface Defect Semantic Segmentation

Abstract

AbstractThis study proposes mix transformer-enhanced UNet (MiTE-UNet), an improved UNet architecture based on a hybrid convolutional neural network (CNN)–transformer framework, for concrete building surface defect segmentation. The proposed model is ...Practical ApplicationsConcrete buildings such as bridges and tunnels often develop surface defects over time, and, if not detected early, these issues may worsen and pose safety risks. Traditional manual inspections are slow and labor-intensive and often ...