# Segmentation Loss Odyssey

arXiv: https://arxiv.org/abs/2005.13449 · HTML: https://mlsanity.com/paper/2005.13449/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 May 2020.

## Built on by (most cited first, 7 of 7)

- [Modality specific U-Net variants for biomedical image segmentation: A survey](https://mlsanity.com/paper/2107.04537/) (2021)
- [Cutting-edge 3D Medical Image Segmentation Methods in 2020: Are Happy Families All Alike?](https://mlsanity.com/paper/2101.00232/) (2021)
- [MD Loss: Efficient Training of 3D Seismic Fault Segmentation Network under Sparse Labels by Weakening Anomaly Annotation](https://mlsanity.com/paper/2110.05319/) (2021)
- [An FPGA smart camera implementation of segmentation models for drone wildfire imagery](https://mlsanity.com/paper/2309.01318/) (2023)
- [Digitizing Paper ECGs at Scale: An Open-Source Algorithm for Clinical Research](https://mlsanity.com/paper/2510.19590/) (2025)
- [SELTO: Sample-Efficient Learned Topology Optimization](https://mlsanity.com/paper/2209.05098/) (2022)
- [Automated Mosaic Tesserae Segmentation via Deep Learning Techniques](https://mlsanity.com/paper/2512.18406/) (2025)

## Abstract (arXiv)

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 urlhttps://github.com/JunMa11/SegLoss.