mlsanityData to 7 Oct 2026

Optimized Hybrid Focal Margin Loss for Crack Segmentation

arXiv 2302.04395 ↗First posted 9 Feb 2023cs.CV eess.IVcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 23 of its 33 references that are in the map. First posted on arXiv 9 Feb 2023.

Builds on

23 of 33 references.

References · 23

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  4. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,284
  5. 2021TransUNet: Transformers Make Strong Encoders for Medical Image Segmentationcited by 1,552
  6. 2018UNet++: A Nested U-Net Architecture for Medical Image Segmentationcited by 1,518
  7. 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,483
  8. 2018Attention U-Net: Learning Where to Look for the Pancreascited by 1,420
  9. 2017Focal Loss for Dense Object Detectioncited by 749
  10. 2014Deeply-Supervised Netscited by 364
  11. 2016Large-Margin Softmax Loss for Convolutional Neural Networkscited by 296
  12. 2016ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentationcited by 291
11 more
  1. 2017Tversky loss function for image segmentation using 3D fully convolutional deep networkscited by 228
  2. 2020A survey of loss functions for semantic segmentationcited by 216
  3. 2018A Novel Focal Tversky loss function with improved Attention U-Net for lesion segmentationcited by 171
  4. 2021Unified Focal loss: Generalising Dice and cross entropy-based losses to handle class imbalanced medical image segmentationcited by 88
  5. 2019Feature Pyramid and Hierarchical Boosting Network for Pavement Crack Detectioncited by 80
  6. 2018Combo Loss: Handling Input and Output Imbalance in Multi-Organ Segmentationcited by 76
  7. 2018AnatomyNet: Deep Learning for Fast and Fully Automated Whole-volume Segmentation of Head and Neck Anatomycited by 54
  8. 2019Overfitting of neural nets under class imbalance: Analysis and improvements for segmentationcited by 27
  9. 2021Focus U-Net: A novel dual attention-gated CNN for polyp segmentation during colonoscopycited by 20
  10. 2020Optimized Deep Encoder-Decoder Methods for Crack Segmentationcited by 10
  11. 2021Encoder-Decoder Architectures for Clinically Relevant Coronary Artery Segmentationcited by 4

Built on by

Not cited yet.