Unsupervised Domain Adaptation for Crack Segmentation via Cross-Domain Stylization and Dual Adversarial Feature Learning

Abstract

AbstractSurface crack segmentation is critical for infrastructure inspection, yet deep-learning-based methods are hampered by their reliance on large annotated data sets and poor generalization across domains due to distribution shifts. While unsupervised ...Practical ApplicationsThis research presents CDE-Crack, an innovative method using artificial intelligence to identify cracks in infrastructure like buildings, bridges, and roads with high accuracy, even when visual data differ across sites. By employing ...