Segmentation Loss Odyssey
arXiv:2005.13449
Abstract
Loss functions are one of the crucial ingredients in deep learning-based medical image segmentation methods. Many loss functions have been proposed in existing literature, but are studied separately or only investigated with few other losses. In this paper, we present a systematic taxonomy to sort existing loss functions into four meaningful categories. This helps to reveal links and fundamental similarities between them. Moreover, we explore the relationship between the traditional region-based and the more recent boundary-based loss functions. The PyTorch implementations of these loss functions are publicly available at \url{https://github.com/JunMa11/SegLoss}.
Educational Materials (https://miccai-sb.github.io/materials/Ma2019.pdf)
References in corpus (5)
- Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations
- Boundary loss for highly unbalanced segmentation
- Asymmetric Loss Functions and Deep Densely Connected Networks for Highly Imbalanced Medical Image Segmentation: Application to Multiple Sclerosis Lesion Detection
- 3D Segmentation with Exponential Logarithmic Loss for Highly Unbalanced Object Sizes
- Bridging Category-level and Instance-level Semantic Image Segmentation
Cited by in corpus (6)
- Modality specific U-Net variants for biomedical image segmentation: A survey
- MD Loss: Efficient Training of 3D Seismic Fault Segmentation Network under Sparse Labels by Weakening Anomaly Annotation
- Cutting-edge 3D Medical Image Segmentation Methods in 2020: Are Happy Families All Alike?
- Auto Seg-Loss: Searching Metric Surrogates for Semantic Segmentation
- Loss Ensembles for Extremely Imbalanced Segmentation
- Combining CNN and Hybrid Active Contours for Head and Neck Tumor Segmentation in CT and PET images