# Bin-wise Temperature Scaling (BTS): Improvement in Confidence Calibration Performance through Simple Scaling Techniques

arXiv: https://arxiv.org/abs/1908.11528 · HTML: https://mlsanity.com/paper/1908.11528/

## Key facts

- Cited by 23 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 30 Aug 2019.

## Built on by (most cited first, 23 of 23)

- [Calibration in Deep Learning: A Survey of the State-of-the-Art](https://mlsanity.com/paper/2308.01222/) (2023)
- [Sample-dependent Adaptive Temperature Scaling for Improved Calibration](https://mlsanity.com/paper/2207.06211/) (2022)
- [Towards Improving Calibration in Object Detection Under Domain Shift](https://mlsanity.com/paper/2209.07601/) (2022)
- [Adaptive Temperature Scaling for Robust Calibration of Deep Neural Networks](https://mlsanity.com/paper/2208.00461/) (2022)
- [Class-Distribution-Aware Calibration for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2109.05263/) (2021)
- [On Temperature Scaling and Conformal Prediction of Deep Classifiers](https://mlsanity.com/paper/2402.05806/) (2024)
- [Bridging Precision and Confidence: A Train-Time Loss for Calibrating Object Detection](https://mlsanity.com/paper/2303.14404/) (2023)
- [Cal-DETR: Calibrated Detection Transformer](https://mlsanity.com/paper/2311.03570/) (2023)
- [Confidence Calibration for Object Detection and Segmentation](https://mlsanity.com/paper/2202.12785/) (2022)
- [Improved post-hoc probability calibration for out-of-domain MRI segmentation](https://mlsanity.com/paper/2208.02870/) (2022)
- [Context-Aware Selective Label Smoothing for Calibrating Sequence Recognition Model](https://mlsanity.com/paper/2303.06946/) (2023)
- [Decoupling Feature Extraction and Classification Layers for Calibrated Neural Networks](https://mlsanity.com/paper/2405.01196/) (2024)
- [Rethinking Semi-supervised Segmentation Beyond Accuracy: Reliability and Robustness](https://mlsanity.com/paper/2506.05917/) (2025)
- [Improving Multi-Class Calibration through Normalization-Aware Isotonic Techniques](https://mlsanity.com/paper/2512.09054/) (2025)
- [h-calibration: Rethinking Classifier Recalibration with Probabilistic Error-Bounded Objective](https://mlsanity.com/paper/2506.17968/) (2025)
- [Perception and Semantic Aware Regularization for Sequential Confidence Calibration](https://mlsanity.com/paper/2305.19498/) (2023)
- [Towards Vector Optimization on Low-Dimensional Vector Symbolic Architecture](https://mlsanity.com/paper/2502.14075/) (2025)
- [To Trust or Not to Trust: On Calibration in ML-based Resource Allocation for Wireless Networks](https://mlsanity.com/paper/2507.17494/) (2025)
- [DA-Cal: Towards Cross-Domain Calibration in Semantic Segmentation](https://mlsanity.com/paper/2602.20860/) (2026)
- [Dual-Branch Temperature Scaling Calibration for Long-Tailed Recognition](https://mlsanity.com/paper/2308.08366/) (2023)
- [Towards Reliable Detection of Empty Space: Conditional Marked Point Processes for Object Detection](https://mlsanity.com/paper/2506.21486/) (2025)
- [Clustered Calibration: Representation-Aware Probability Calibration via Learned Subpopulations](https://mlsanity.com/paper/2510.19328/) (2025)
- [The Impact of CutMix on Reliability and Robustness in Semantic Segmentation](https://mlsanity.com/paper/2608.18715/) (2026)

## Abstract (arXiv)

The prediction reliability of neural networks is important in many applications. Specifically, in safety-critical domains, such as cancer prediction or autonomous driving, a reliable confidence of model's prediction is critical for the interpretation of the results. Modern deep neural networks have achieved a significant improvement in performance for many different image classification tasks. However, these networks tend to be poorly calibrated in terms of output confidence. Temperature scaling is an efficient post-processing-based calibration scheme and obtains well calibrated results. In this study, we leverage the concept of temperature scaling to build a sophisticated bin-wise scaling. Furthermore, we adopt augmentation of validation samples for elaborated scaling. The proposed methods consistently improve calibration performance with various datasets and deep convolutional neural network models.