Optimized Hybrid Focal Margin Loss for Crack Segmentation

TL;DR

This paper introduces a novel hybrid focal margin loss that combines large-margin softmax and focal loss to effectively address class imbalance and overfitting in crack segmentation, showing significant improvements in IoU scores.

Contribution

A unified loss function that merges large-margin softmax and focal loss for improved crack segmentation performance, addressing class imbalance and overfitting simultaneously.

Findings

Significant IoU improvements on multiple datasets.

Effective handling of class imbalance in crack segmentation.

Enhanced model robustness against overfitting.

Abstract

Many loss functions have been derived from cross-entropy loss functions such as large-margin softmax loss and focal loss. The large-margin softmax loss makes the classification more rigorous and prevents overfitting. The focal loss alleviates class imbalance in object detection by down-weighting the loss of well-classified examples. Recent research has shown that these two loss functions derived from cross entropy have valuable applications in the field of image segmentation. However, to the best of our knowledge, there is no unified formulation that combines these two loss functions so that they can not only be transformed mutually, but can also be used to simultaneously address class imbalance and overfitting. To this end, we subdivide the entropy-based loss into the regularizer-based entropy loss and the focal-based entropy loss, and propose a novel optimized hybrid focal loss to handle extreme class imbalance and prevent overfitting for crack segmentation. We have evaluated our proposal in comparison with three crack segmentation datasets (DeepCrack-DB, CRACK500 and our private PanelCrack dataset). Our experiments demonstrate that the focal margin component can significantly increase the IoU of cracks by 0.43 on DeepCrack-DB and 0.44 on our PanelCrack dataset, respectively.