Lightweight convolutional neural network driven by small data for asphalt pavement crack segmentation

A lightweight PCSNet-based segmentation model is developed to efficiently overcome insufficient performance in feature extraction and boundary loss information resulting from sampling operations. The proposed approach incorporates two key components: an enhanced shuffle unit and an improved inverted residual architecture to effectively reduce model parameters and enhance inference time. Additionally, introducing the generalized Dice loss (GDL) aims to address the prediction accuracy issue caused by category imbalance. Finally, this study employs gradient-based class activation mapping to visualize and interpret the learned features. To enhance model interpretability, experiments were conducted on three publicly available datasets and compared with existing popular segmentation models. The findings demonstrate that including the GDL in the lightweight PCSNet model leads to a significant improvement in prediction performance, with the highest mIoU reaching 78.93%. Additionally, the visualization of class activation mapping (CAM) further enhances PCSNet interpretability in terms of feature extraction.

Automated summary

A lightweight PCSNet-based segmentation model is developed to address the issues of insufficient performance in feature extraction and boundary loss information. The introduction of generalized Dice loss improves prediction performance, and the visualization of class activation mapping enhances model interpretability.