Two-stage framework with improved U-Net based on self-supervised contrastive learning for pavement crack segmentation
Qingsong Song, Wei Yao, Haojiang Tian, Yidan Guo, Ravie Chandren Muniyandi, Yisheng An
Topics & Concepts
Computer scienceArtificial intelligenceSegmentationResidualFeature (linguistics)Pattern recognition (psychology)Semi-supervised learningDeep learningSupervised learningFeature vectorMachine learningFeature learningGround truthRepresentation (politics)Stage (stratigraphy)Artificial neural networkGeologyAlgorithmLinguisticsPhilosophyPoliticsPaleontologyPolitical scienceLawInfrastructure Maintenance and MonitoringConcrete Corrosion and DurabilityAsphalt Pavement Performance Evaluation