# blob loss: instance imbalance aware loss functions for semantic segmentation

arXiv: https://arxiv.org/abs/2205.08209 · HTML: https://mlsanity.com/paper/2205.08209/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 36 references that are in the map.
- First posted on arXiv 17 May 2022.

## Builds on (most cited first, 18 of 18)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [UNETR: Transformers for 3D Medical Image Segmentation](https://mlsanity.com/paper/2103.10504/) (2021)
- [Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations](https://mlsanity.com/paper/1707.03237/) (2017)
- [The Liver Tumor Segmentation Benchmark (LiTS)](https://mlsanity.com/paper/1901.04056/) (2019)
- [clDice -- A Novel Topology-Preserving Loss Function for Tubular Structure Segmentation](https://mlsanity.com/paper/2003.07311/) (2020)
- [Tversky loss function for image segmentation using 3D fully convolutional deep networks](https://mlsanity.com/paper/1706.05721/) (2017)
- [Mish: A Self Regularized Non-Monotonic Activation Function](https://mlsanity.com/paper/1908.08681/) (2019)
- [AnatomyNet: Deep Learning for Fast and Fully Automated Whole-volume Segmentation of Head and Neck Anatomy](https://mlsanity.com/paper/1808.05238/) (2018)
- [Optimization for Medical Image Segmentation: Theory and Practice when evaluating with Dice Score or Jaccard Index](https://mlsanity.com/paper/2010.13499/) (2020)
- [Automated Design of Deep Learning Methods for Biomedical Image Segmentation](https://mlsanity.com/paper/1904.08128/) (2019)
- [Are we using appropriate segmentation metrics? Identifying correlates of human expert perception for CNN training beyond rolling the DICE coefficient](https://mlsanity.com/paper/2103.06205/) (2021)
- [Ranger21: a synergistic deep learning optimizer](https://mlsanity.com/paper/2106.13731/) (2021)
- [Generalised Wasserstein Dice Score for Imbalanced Multi-class Segmentation using Holistic Convolutional Networks](https://mlsanity.com/paper/1707.00478/) (2017)
- [pymia: A Python package for data handling and evaluation in deep learning-based medical image analysis](https://mlsanity.com/paper/2010.03639/) (2020)
- [Universal Loss Reweighting to Balance Lesion Size Inequality in 3D Medical Image Segmentation](https://mlsanity.com/paper/2007.10033/) (2020)

## Built on by (most cited first, 18 of 18)

- [Metrics reloaded: Recommendations for image analysis validation](https://mlsanity.com/paper/2206.01653/) (2022)
- [Where is VALDO? VAscular Lesions Detection and segmentatiOn challenge at MICCAI 2021](https://mlsanity.com/paper/2208.07167/) (2022)
- [Panoptica -- instance-wise evaluation of 3D semantic and instance segmentation maps](https://mlsanity.com/paper/2312.02608/) (2023)
- [Improving Segmentation of Objects with Varying Sizes in Biomedical Images using Instance-wise and Center-of-Instance Segmentation Loss Function](https://mlsanity.com/paper/2304.06229/) (2023)
- [Learning to Look Closer: A New Instance-Wise Loss for Small Cerebral Lesion Segmentation](https://mlsanity.com/paper/2511.17146/) (2025)
- [Primitive Simultaneous Optimization of Similarity Metrics for Image Registration](https://mlsanity.com/paper/2304.01601/) (2023)
- [Exploiting XAI maps to improve MS lesion segmentation and detection in MRI](https://mlsanity.com/paper/2409.03772/) (2024)
- [Complex Wavelet Mutual Information Loss: A Multi-Scale Loss Function for Semantic Segmentation](https://mlsanity.com/paper/2502.00563/) (2025)
- [Adaptive Voxel-Weighted Loss Using L1 Norms in Deep Neural Networks for Detection and Segmentation of Prostate Cancer Lesions in PET/CT Images](https://mlsanity.com/paper/2502.02756/) (2025)
- [Benchmarking and Explaining Deep Learning Cortical Lesion MRI Segmentation in Multiple Sclerosis](https://mlsanity.com/paper/2507.12092/) (2025)
- [Instance Awareness of Multi-class Semantic Segmentation Loss Functions](https://mlsanity.com/paper/2604.24276/) (2026)
- [Redefining Instance Matching: A Unified Framework for Part-Aware Matching in Panoptic Segmentation Evaluation](https://mlsanity.com/paper/2605.31094/) (2026)
- [Automated Ensemble-Based Segmentation of Adult Brain Tumors: A Novel Approach Using the BraTS AFRICA Challenge Data](https://mlsanity.com/paper/2308.07214/) (2023)
- [All Sizes Matter: Improving Volumetric Brain Segmentation on Small Lesions](https://mlsanity.com/paper/2310.02829/) (2023)
- [Instance-level quantitative saliency in multiple sclerosis lesion segmentation](https://mlsanity.com/paper/2406.09335/) (2024)
- [Component-Adaptive and Lesion-Level Supervision for Improved Small Structure Segmentation in Brain MRI](https://mlsanity.com/paper/2604.08015/) (2026)
- [Focus on What Matters: Two-Stage ROI-Aware Refinement for Anatomy-Preserving Fetal Ultrasound Reconstruction](https://mlsanity.com/paper/2604.23839/) (2026)
- [BiCC: Bidirectional Connected-Component Loss for Instance-Aware Segmentation](https://mlsanity.com/paper/2609.30223/) (2026)

## Abstract (arXiv)

Deep convolutional neural networks (CNN) have proven to be remarkably effective in semantic segmentation tasks. Most popular loss functions were introduced targeting improved volumetric scores, such as the Dice coefficient (DSC). By design, DSC can tackle class imbalance, however, it does not recognize instance imbalance within a class. As a result, a large foreground instance can dominate minor instances and still produce a satisfactory DSC. Nevertheless, detecting tiny instances is crucial for many applications, such as disease monitoring. For example, it is imperative to locate and surveil small-scale lesions in the follow-up of multiple sclerosis patients. We propose a novel family of loss functions, blob loss, primarily aimed at maximizing instance-level detection metrics, such as F1 score and sensitivity. Blob loss is designed for semantic segmentation problems where detecting multiple instances matters. We extensively evaluate a DSC-based blob loss in five complex 3D semantic segmentation tasks featuring pronounced instance heterogeneity in terms of texture and morphology. Compared to soft Dice loss, we achieve 5% improvement for MS lesions, 3% improvement for liver tumor, and an average 2% improvement for microscopy segmentation tasks considering F1 score.