# Boundary-weighted logit consistency improves calibration of segmentation networks

arXiv: https://arxiv.org/abs/2307.08163 · HTML: https://mlsanity.com/paper/2307.08163/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 38 references that are in the map.
- First posted on arXiv 16 Jul 2023.

## Builds on (most cited first, 23 of 23)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [When Does Label Smoothing Help?](https://mlsanity.com/paper/1906.02629/) (2019)
- [Measuring Calibration in Deep Learning](https://mlsanity.com/paper/1904.01685/) (2019)
- [Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learning](https://mlsanity.com/paper/1606.04586/) (2016)
- [A Probabilistic U-Net for Segmentation of Ambiguous Images](https://mlsanity.com/paper/1806.05034/) (2018)
- [Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks](https://mlsanity.com/paper/1807.07356/) (2018)
- [Confidence Calibration and Predictive Uncertainty Estimation for Deep Medical Image Segmentation](https://mlsanity.com/paper/1911.13273/) (2019)
- [Ensemble of Averages: Improving Model Selection and Boosting Performance in Domain Generalization](https://mlsanity.com/paper/2110.10832/) (2021)
- [Transformation Consistent Self-ensembling Model for Semi-supervised Medical Image Segmentation](https://mlsanity.com/paper/1903.00348/) (2019)
- [PHiSeg: Capturing Uncertainty in Medical Image Segmentation](https://mlsanity.com/paper/1906.04045/) (2019)
- [SynthStrip: Skull-Stripping for Any Brain Image](https://mlsanity.com/paper/2203.09974/) (2022)
- [Mutual Consistency Learning for Semi-supervised Medical Image Segmentation](https://mlsanity.com/paper/2109.09960/) (2021)
- [Stochastic Segmentation Networks: Modelling Spatially Correlated Aleatoric Uncertainty](https://mlsanity.com/paper/2006.06015/) (2020)
- [The Devil is in the Margin: Margin-based Label Smoothing for Network Calibration](https://mlsanity.com/paper/2111.15430/) (2021)
- [Generalized Jensen-Shannon Divergence Loss for Learning with Noisy Labels](https://mlsanity.com/paper/2105.04522/) (2021)
- [Semi-Supervised Medical Image Segmentation via Learning Consistency under Transformations](https://mlsanity.com/paper/1911.01218/) (2019)
- [Semi-Supervised Brain Lesion Segmentation with an Adapted Mean Teacher Model](https://mlsanity.com/paper/1903.01248/) (2019)
- [Spatially Varying Label Smoothing: Capturing Uncertainty from Expert Annotations](https://mlsanity.com/paper/2104.05788/) (2021)
- [Maximum Entropy on Erroneous Predictions (MEEP): Improving model calibration for medical image segmentation](https://mlsanity.com/paper/2112.12218/) (2021)
- [Trust your neighbours: Penalty-based constraints for model calibration](https://mlsanity.com/paper/2303.06268/) (2023)
- [Automatic Segmentation of the Placenta in BOLD MRI Time Series](https://mlsanity.com/paper/2208.02895/) (2022)
- [Hypernet-Ensemble Learning of Segmentation Probability for Medical Image Segmentation with Ambiguous Labels](https://mlsanity.com/paper/2112.06693/) (2021)

## Built on by (most cited first, 4 of 4)

- [Class and Region-Adaptive Constraints for Network Calibration](https://mlsanity.com/paper/2403.12364/) (2024)
- [Consistency Regularization Improves Placenta Segmentation in Fetal EPI MRI Time Series](https://mlsanity.com/paper/2310.03870/) (2023)
- [Explaining Uncertainty in Multiple Sclerosis Cortical Lesion Segmentation Beyond Prediction Errors](https://mlsanity.com/paper/2504.04814/) (2025)
- [Beyond scalar losses: calibrating segmentation models via gradient vector field surgery](https://mlsanity.com/paper/2607.14338/) (2026)

## Abstract (arXiv)

Neural network prediction probabilities and accuracy are often only weakly-correlated. Inherent label ambiguity in training data for image segmentation aggravates such miscalibration. We show that logit consistency across stochastic transformations acts as a spatially varying regularizer that prevents overconfident predictions at pixels with ambiguous labels. Our boundary-weighted extension of this regularizer provides state-of-the-art calibration for prostate and heart MRI segmentation.