Fast and Accurate Road Crack Detection Based on Adaptive Cost-Sensitive Loss Function
This work addresses a domain-specific issue in computer vision for road maintenance applications, but it is incremental as it builds on existing loss function modifications.
The paper tackles the problem of foreground-background imbalance in road crack detection by proposing an adaptive cost-sensitive loss function, which speeds up training while maintaining test accuracy across four public datasets.
Numerous detection problems in computer vision, including road crack detection, suffer from exceedingly foreground-background imbalance. Fortunately, modification of loss function appears to solve this puzzle once and for all. In this paper, we propose a pixel-based adaptive weighted cross-entropy loss in conjunction with Jaccard distance to facilitate high-quality pixel-level road crack detection. Our work profoundly demonstrates the influence of loss functions on detection outcomes, and sheds light on the sophisticated consecutive improvements in the realm of crack detection. Specifically, to verify the effectiveness of the proposed loss, we conduct extensive experiments on four public databases, i.e., CrackForest, AigleRN, Crack360, and BJN260. Compared with the vanilla weighted cross-entropy, the proposed loss significantly speeds up the training process while retaining the test accuracy.