# Attended Temperature Scaling: A Practical Approach for Calibrating Deep Neural Networks

arXiv: https://arxiv.org/abs/1810.11586 · HTML: https://mlsanity.com/paper/1810.11586/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Oct 2018.

## Built on by (most cited first, 21 of 21)

- [Calibration in Deep Learning: A Survey of the State-of-the-Art](https://mlsanity.com/paper/2308.01222/) (2023)
- [Your Pre-trained LLM is Secretly an Unsupervised Confidence Calibrator](https://mlsanity.com/paper/2505.16690/) (2025)
- [Class-Distribution-Aware Calibration for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2109.05263/) (2021)
- [MBCT: Tree-Based Feature-Aware Binning for Individual Uncertainty Calibration](https://mlsanity.com/paper/2202.04348/) (2022)
- [Confidence-Aware Multi-Field Model Calibration](https://mlsanity.com/paper/2402.17655/) (2024)
- [Improving Multi-Class Calibration through Normalization-Aware Isotonic Techniques](https://mlsanity.com/paper/2512.09054/) (2025)
- [Going Beyond One-Hot Encoding in Classification: Can Human Uncertainty Improve Model Performance?](https://mlsanity.com/paper/2205.15265/) (2022)
- [Towards Unbiased Calibration using Meta-Regularization](https://mlsanity.com/paper/2303.15057/) (2023)
- [Perception and Semantic Aware Regularization for Sequential Confidence Calibration](https://mlsanity.com/paper/2305.19498/) (2023)
- [Probability Bounding: Post-Hoc Calibration via Box-Constrained Softmax](https://mlsanity.com/paper/2506.10572/) (2025)
- [Evaluating Temperature Scaling Calibration Effectiveness for CNNs under Varying Noise Levels in Brain Tumour Detection](https://mlsanity.com/paper/2509.24951/) (2025)
- [The Well-Tempered Classifier: Some Elementary Properties of Temperature Scaling](https://mlsanity.com/paper/2602.14862/) (2026)
- [DA-Cal: Towards Cross-Domain Calibration in Semantic Segmentation](https://mlsanity.com/paper/2602.20860/) (2026)
- [HypeLoRA: Hyper-Network-Generated LoRA Adapters for Calibrated Language Model Fine-Tuning](https://mlsanity.com/paper/2603.19278/) (2026)
- [Uncertainty Estimation based on Geometric Separation](https://mlsanity.com/paper/2301.04452/) (2023)
- [A Saliency-based Clustering Framework for Identifying Aberrant Predictions](https://mlsanity.com/paper/2311.06454/) (2023)
- [Learning LLM Preference over Intra-Dialogue Pairs: A Framework for Utterance-level Understandings](https://mlsanity.com/paper/2503.05620/) (2025)
- [Towards Calibration Enhanced Network by Inverse Adversarial Attack](https://mlsanity.com/paper/2504.06358/) (2025)
- [XplaiNLP at CheckThat! 2025: Multilingual Subjectivity Detection with Finetuned Transformers and Prompt-Based Inference with Large Language Models](https://mlsanity.com/paper/2509.12130/) (2025)
- [Knob: A Physics-Inspired Gating Interface for Interpretable and Controllable Neural Dynamics](https://mlsanity.com/paper/2602.22702/) (2026)
- [ADS-C: Antidistillation Sampling for Classification](https://mlsanity.com/paper/2607.15467/) (2026)

## Abstract (arXiv)

Recently, Deep Neural Networks (DNNs) have been achieving impressive results on wide range of tasks. However, they suffer from being well-calibrated. In decision-making applications, such as autonomous driving or medical diagnosing, the confidence of deep networks plays an important role to bring the trust and reliability to the system. To calibrate the deep networks' confidence, many probabilistic and measure-based approaches are proposed. Temperature Scaling (TS) is a state-of-the-art among measure-based calibration methods which has low time and memory complexity as well as effectiveness. In this paper, we study TS and show it does not work properly when the validation set that TS uses for calibration has small size or contains noisy-labeled samples. TS also cannot calibrate highly accurate networks as well as non-highly accurate ones. Accordingly, we propose Attended Temperature Scaling (ATS) which preserves the advantages of TS while improves calibration in aforementioned challenging situations. We provide theoretical justifications for ATS and assess its effectiveness on wide range of deep models and datasets. We also compare the calibration results of TS and ATS on skin lesion detection application as a practical problem where well-calibrated system can play important role in making a decision.