CrackGAN: Pavement Crack Detection Using Partially Accurate Ground Truths Based on Generative Adversarial Learning

Abstract

Fully convolutional network is a powerful tool for per-pixel semantic segmentation/detection. However, it is problematic when coping with crack detection using partially accurate ground truths (GTs): the network may easily converge to the status that treats all the pixels as background (BG) and still achieves a very good loss, named "All Black" phenomenon, due to the unavailability of accurate GTs and the data imbalance. To tackle this problem, we propose crack-patch-only (CPO) supervised generative adversarial learning for end-to-end training, which forces the network to always produce crack-GT images while reserves both crack and BG-image translation abilities by feeding a larger-size crack image into an asymmetric U-shape generator to overcome the "All Black" issue. The proposed approach is validated using four crack datasets; and achieves state-of-the-art performance comparing with that of the recently published works in efficiency and accuracy.

References in corpus (7)

• Adam: A Method for Stochastic Optimization
• Conditional Generative Adversarial Nets
• Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
• How transferable are features in deep neural networks?
• Fully Convolutional Networks for Semantic Segmentation
• Richer Convolutional Features for Edge Detection
• Feature Pyramid and Hierarchical Boosting Network for Pavement Crack Detection

Cited by in corpus (7)

• Deep Learning for Segmentation of Cracks in High-Resolution Images of Steel Bridges
• CrackCLF: Automatic Pavement Crack Detection based on Closed-Loop Feedback
• Joint Learning of Blind Super-Resolution and Crack Segmentation for Realistic Degraded Images
• SCNet: A Generalized Attention-based Model for Crack Fault Segmentation
• Vision-Guided Active Tactile Perception for Crack Detection and Reconstruction
• TB-Net: A Three-Stream Boundary-Aware Network for Fine-Grained Pavement Disease Segmentation
• Deep Domain Adaptation for Pavement Crack Detection