# Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations

arXiv: https://arxiv.org/abs/1707.03237 · HTML: https://mlsanity.com/paper/1707.03237/

## Key facts

- Cited by 620 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Jul 2017.

## Built on by (most cited first, 30 of 620)

- [Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstruction](https://mlsanity.com/paper/2109.00512/) (2021)
- [Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives](https://mlsanity.com/paper/2311.18259/) (2023)
- [MONAI: An open-source framework for deep learning in healthcare](https://mlsanity.com/paper/2211.02701/) (2022)
- [Medical Image Segmentation Review: The success of U-Net](https://mlsanity.com/paper/2211.14830/) (2022)
- [UNetFormer: A UNet-like Transformer for Efficient Semantic Segmentation of Remote Sensing Urban Scene Imagery](https://mlsanity.com/paper/2109.08937/) (2021)
- [FakeShield: Explainable Image Forgery Detection and Localization via Multi-modal Large Language Models](https://mlsanity.com/paper/2410.02761/) (2024)
- [Recent advances and clinical applications of deep learning in medical image analysis](https://mlsanity.com/paper/2105.13381/) (2021)
- [PSALM: Pixelwise SegmentAtion with Large Multi-Modal Model](https://mlsanity.com/paper/2403.14598/) (2024)
- [UniverSeg: Universal Medical Image Segmentation](https://mlsanity.com/paper/2304.06131/) (2023)
- [Unified Focal loss: Generalising Dice and cross entropy-based losses to handle class imbalanced medical image segmentation](https://mlsanity.com/paper/2102.04525/) (2021)
- [Federated Learning Enables Big Data for Rare Cancer Boundary Detection](https://mlsanity.com/paper/2204.10836/) (2022)
- [Infrared Small Target Detection with Scale and Location Sensitivity](https://mlsanity.com/paper/2403.19366/) (2024)
- [MiM-ISTD: Mamba-in-Mamba for Efficient Infrared Small Target Detection](https://mlsanity.com/paper/2403.02148/) (2024)
- [Common Limitations of Image Processing Metrics: A Picture Story](https://mlsanity.com/paper/2104.05642/) (2021)
- [PerceptionGPT: Effectively Fusing Visual Perception into LLM](https://mlsanity.com/paper/2311.06612/) (2023)
- [SAR-RARP50: Segmentation of surgical instrumentation and Action Recognition on Robot-Assisted Radical Prostatectomy Challenge](https://mlsanity.com/paper/2401.00496/) (2023)
- [ImageCAS: A Large-Scale Dataset and Benchmark for Coronary Artery Segmentation based on Computed Tomography Angiography Images](https://mlsanity.com/paper/2211.01607/) (2022)
- [Online Detection of AI-Generated Images](https://mlsanity.com/paper/2310.15150/) (2023)
- [Hierarchical Open-vocabulary Universal Image Segmentation](https://mlsanity.com/paper/2307.00764/) (2023)
- [ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution](https://mlsanity.com/paper/2303.00246/) (2023)
- [Deep Learning Approaches for Data Augmentation in Medical Imaging: A Review](https://mlsanity.com/paper/2307.13125/) (2023)
- [CDMamba: Incorporating Local Clues into Mamba for Remote Sensing Image Binary Change Detection](https://mlsanity.com/paper/2406.04207/) (2024)
- [Make It Count: Text-to-Image Generation with an Accurate Number of Objects](https://mlsanity.com/paper/2406.10210/) (2024)
- [SplineGS: Robust Motion-Adaptive Spline for Real-Time Dynamic 3D Gaussians from Monocular Video](https://mlsanity.com/paper/2412.09982/) (2024)
- [PolyWorld: Polygonal Building Extraction with Graph Neural Networks in Satellite Images](https://mlsanity.com/paper/2111.15491/) (2021)
- [EdgeSAM: Prompt-In-the-Loop Distillation for SAM](https://mlsanity.com/paper/2312.06660/) (2023)
- [Active Boundary Loss for Semantic Segmentation](https://mlsanity.com/paper/2102.02696/) (2021)
- [TraSeTR: Track-to-Segment Transformer with Contrastive Query for Instance-level Instrument Segmentation in Robotic Surgery](https://mlsanity.com/paper/2202.08453/) (2022)
- [DreamTeacher: Pretraining Image Backbones with Deep Generative Models](https://mlsanity.com/paper/2307.07487/) (2023)
- [RobustSAM: Segment Anything Robustly on Degraded Images](https://mlsanity.com/paper/2406.09627/) (2024)

## Abstract (arXiv)

Deep-learning has proved in recent years to be a powerful tool for image analysis and is now widely used to segment both 2D and 3D medical images. Deep-learning segmentation frameworks rely not only on the choice of network architecture but also on the choice of loss function. When the segmentation process targets rare observations, a severe class imbalance is likely to occur between candidate labels, thus resulting in sub-optimal performance. In order to mitigate this issue, strategies such as the weighted cross-entropy function, the sensitivity function or the Dice loss function, have been proposed. In this work, we investigate the behavior of these loss functions and their sensitivity to learning rate tuning in the presence of different rates of label imbalance across 2D and 3D segmentation tasks. We also propose to use the class re-balancing properties of the Generalized Dice overlap, a known metric for segmentation assessment, as a robust and accurate deep-learning loss function for unbalanced tasks.