# Local Temperature Scaling for Probability Calibration

arXiv: https://arxiv.org/abs/2008.05105 · HTML: https://mlsanity.com/paper/2008.05105/

## Key facts

- Cited by 95 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Aug 2020.

## Built on by (most cited first, 30 of 95)

- [SimpleClick: Interactive Image Segmentation with Simple Vision Transformers](https://mlsanity.com/paper/2210.11006/) (2022)
- [The Devil is in the Margin: Margin-based Label Smoothing for Network Calibration](https://mlsanity.com/paper/2111.15430/) (2021)
- [Calibration in Deep Learning: A Survey of the State-of-the-Art](https://mlsanity.com/paper/2308.01222/) (2023)
- [Classifier Calibration: A survey on how to assess and improve predicted class probabilities](https://mlsanity.com/paper/2112.10327/) (2021)
- [A Stitch in Time Saves Nine: A Train-Time Regularizing Loss for Improved Neural Network Calibration](https://mlsanity.com/paper/2203.13834/) (2022)
- [Sample-dependent Adaptive Temperature Scaling for Improved Calibration](https://mlsanity.com/paper/2207.06211/) (2022)
- [PseudoClick: Interactive Image Segmentation with Click Imitation](https://mlsanity.com/paper/2207.05282/) (2022)
- [Don't Just Blame Over-parametrization for Over-confidence: Theoretical Analysis of Calibration in Binary Classification](https://mlsanity.com/paper/2102.07856/) (2021)
- [A comprehensive survey on deep active learning in medical image analysis](https://mlsanity.com/paper/2310.14230/) (2023)
- [Meta-Cal: Well-controlled Post-hoc Calibration by Ranking](https://mlsanity.com/paper/2105.04290/) (2021)
- [On Calibrating Semantic Segmentation Models: Analyses and An Algorithm](https://mlsanity.com/paper/2212.12053/) (2022)
- [Adaptive Temperature Scaling for Robust Calibration of Deep Neural Networks](https://mlsanity.com/paper/2208.00461/) (2022)
- [DomainAdaptor: A Novel Approach to Test-time Adaptation](https://mlsanity.com/paper/2308.10297/) (2023)
- [Adaptive Preference Scaling for Reinforcement Learning with Human Feedback](https://mlsanity.com/paper/2406.02764/) (2024)
- [Class-Distribution-Aware Calibration for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2109.05263/) (2021)
- [RankMixup: Ranking-Based Mixup Training for Network Calibration](https://mlsanity.com/paper/2308.11990/) (2023)
- [Reliability in Semantic Segmentation: Are We on the Right Track?](https://mlsanity.com/paper/2303.11298/) (2023)
- [ACLS: Adaptive and Conditional Label Smoothing for Network Calibration](https://mlsanity.com/paper/2308.11911/) (2023)
- [Class Adaptive Network Calibration](https://mlsanity.com/paper/2211.15088/) (2022)
- [On Temperature Scaling and Conformal Prediction of Deep Classifiers](https://mlsanity.com/paper/2402.05806/) (2024)
- [Know Where You're Uncertain When Planning with Multimodal Foundation Models: A Formal Framework](https://mlsanity.com/paper/2411.01639/) (2024)
- [Are foundation models for computer vision good conformal predictors?](https://mlsanity.com/paper/2412.06082/) (2024)
- [Jaccard Metric Losses: Optimizing the Jaccard Index with Soft Labels](https://mlsanity.com/paper/2302.05666/) (2023)
- [Trust your neighbours: Penalty-based constraints for model calibration](https://mlsanity.com/paper/2303.06268/) (2023)
- [Bridging Precision and Confidence: A Train-Time Loss for Calibrating Object Detection](https://mlsanity.com/paper/2303.14404/) (2023)
- [Brain-ID: Learning Contrast-agnostic Anatomical Representations for Brain Imaging](https://mlsanity.com/paper/2311.16914/) (2023)
- [Calib3D: Calibrating Model Preferences for Reliable 3D Scene Understanding](https://mlsanity.com/paper/2403.17010/) (2024)
- [Interpretable Uncertainty Quantification in AI for HEP](https://mlsanity.com/paper/2208.03284/) (2022)
- [Multi-Head Multi-Loss Model Calibration](https://mlsanity.com/paper/2303.01099/) (2023)
- [VSR-Net: Vessel-like Structure Rehabilitation Network with Graph Clustering](https://mlsanity.com/paper/2312.13116/) (2023)

## Abstract (arXiv)

For semantic segmentation, label probabilities are often uncalibrated as they are typically only the by-product of a segmentation task. Intersection over Union (IoU) and Dice score are often used as criteria for segmentation success, while metrics related to label probabilities are not often explored. However, probability calibration approaches have been studied, which match probability outputs with experimentally observed errors. These approaches mainly focus on classification tasks, but not on semantic segmentation. Thus, we propose a learning-based calibration method that focuses on multi-label semantic segmentation. Specifically, we adopt a convolutional neural network to predict local temperature values for probability calibration. One advantage of our approach is that it does not change prediction accuracy, hence allowing for calibration as a post-processing step. Experiments on the COCO, CamVid, and LPBA40 datasets demonstrate improved calibration performance for a range of different metrics. We also demonstrate the good performance of our method for multi-atlas brain segmentation from magnetic resonance images.