# Rethinking Confidence Calibration for Failure Prediction

arXiv: https://arxiv.org/abs/2303.02970 · HTML: https://mlsanity.com/paper/2303.02970/

## Key facts

- Cited by 43 papers in the map (data through 14 Oct 2026).
- Builds on 61 of its 80 references that are in the map.
- First posted on arXiv 6 Mar 2023.

## Builds on (most cited first, 30 of 61)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks](https://mlsanity.com/paper/1807.03888/) (2018)
- [MLP-Mixer: An all-MLP Architecture for Vision](https://mlsanity.com/paper/2105.01601/) (2021)
- [Sharpness-Aware Minimization for Efficiently Improving Generalization](https://mlsanity.com/paper/2010.01412/) (2020)
- [Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks](https://mlsanity.com/paper/1706.02690/) (2017)
- [Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift](https://mlsanity.com/paper/1906.02530/) (2019)
- [Averaging Weights Leads to Wider Optima and Better Generalization](https://mlsanity.com/paper/1803.05407/) (2018)
- [End to End Learning for Self-Driving Cars](https://mlsanity.com/paper/1604.07316/) (2016)
- [When Does Label Smoothing Help?](https://mlsanity.com/paper/1906.02629/) (2019)
- [Deep Anomaly Detection with Outlier Exposure](https://mlsanity.com/paper/1812.04606/) (2018)
- [AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty](https://mlsanity.com/paper/1912.02781/) (2019)
- [Selective Classification for Deep Neural Networks](https://mlsanity.com/paper/1705.08500/) (2017)
- [A Simple Baseline for Bayesian Uncertainty in Deep Learning](https://mlsanity.com/paper/1902.02476/) (2019)
- [Overfitting in adversarially robust deep learning](https://mlsanity.com/paper/2002.11569/) (2020)
- [Regularizing Neural Networks by Penalizing Confident Output Distributions](https://mlsanity.com/paper/1701.06548/) (2017)
- [Measuring Calibration in Deep Learning](https://mlsanity.com/paper/1904.01685/) (2019)
- [SWAD: Domain Generalization by Seeking Flat Minima](https://mlsanity.com/paper/2102.08604/) (2021)

## Built on by (most cited first, 30 of 43)

- [Self-Alignment for Factuality: Mitigating Hallucinations in LLMs via Self-Evaluation](https://mlsanity.com/paper/2402.09267/) (2024)
- [OpenMix: Exploring Outlier Samples for Misclassification Detection](https://mlsanity.com/paper/2303.17093/) (2023)
- [Overcoming Common Flaws in the Evaluation of Selective Classification Systems](https://mlsanity.com/paper/2407.01032/) (2024)
- [Active Generalized Category Discovery](https://mlsanity.com/paper/2403.04272/) (2024)
- [How to Fix a Broken Confidence Estimator: Evaluating Post-hoc Methods for Selective Classification with Deep Neural Networks](https://mlsanity.com/paper/2305.15508/) (2023)
- [A Data-Driven Measure of Relative Uncertainty for Misclassification Detection](https://mlsanity.com/paper/2306.01710/) (2023)
- [Two Sides of Miscalibration: Identifying Over and Under-Confidence Prediction for Network Calibration](https://mlsanity.com/paper/2308.03172/) (2023)
- [Towards Understanding Why Label Smoothing Degrades Selective Classification and How to Fix It](https://mlsanity.com/paper/2403.14715/) (2024)
- [Monitoring Risks in Test-Time Adaptation](https://mlsanity.com/paper/2507.08721/) (2025)
- [Revisiting Confidence Estimation: Towards Reliable Failure Prediction](https://mlsanity.com/paper/2403.02886/) (2024)
- [Unified Classification and Rejection: A One-versus-All Framework](https://mlsanity.com/paper/2311.13355/) (2023)
- [SURE: SUrvey REcipes for building reliable and robust deep networks](https://mlsanity.com/paper/2403.00543/) (2024)
- [PASS++: A Dual Bias Reduction Framework for Non-Exemplar Class-Incremental Learning](https://mlsanity.com/paper/2407.14029/) (2024)
- [Interpretable Failure Detection with Human-Level Concepts](https://mlsanity.com/paper/2502.05275/) (2025)
- [DECIDER: Leveraging Foundation Model Priors for Improved Model Failure Detection and Explanation](https://mlsanity.com/paper/2408.00331/) (2024)
- [Typicalness-Aware Learning for Failure Detection](https://mlsanity.com/paper/2411.01981/) (2024)
- [Image-Caption Encoding for Improving Zero-Shot Generalization](https://mlsanity.com/paper/2402.02662/) (2024)
- [A Hybrid of Generative and Discriminative Models Based on the Gaussian-coupled Softmax Layer](https://mlsanity.com/paper/2305.05912/) (2023)
- [Empirical Optimal Risk to Quantify Model Trustworthiness for Failure Detection](https://mlsanity.com/paper/2308.03179/) (2023)
- [Towards Calibrated Deep Clustering Network](https://mlsanity.com/paper/2403.02998/) (2024)
- [MaxSup: Overcoming Representation Collapse in Label Smoothing](https://mlsanity.com/paper/2502.15798/) (2025)
- [Pearls from Pebbles: Improved Confidence Functions for Auto-labeling](https://mlsanity.com/paper/2404.16188/) (2024)
- [A Rate-Distortion View of Uncertainty Quantification](https://mlsanity.com/paper/2406.10775/) (2024)
- [h-calibration: Rethinking Classifier Recalibration with Probabilistic Error-Bounded Objective](https://mlsanity.com/paper/2506.17968/) (2025)
- [What Does It Take to Build a Performant Selective Classifier?](https://mlsanity.com/paper/2510.20242/) (2025)
- [CAST: Cluster-Aware Self-Training for Tabular Data via Reliable Confidence](https://mlsanity.com/paper/2310.06380/) (2023)
- [Evaluation and Improvement of Fault Detection for Large Language Models](https://mlsanity.com/paper/2404.14419/) (2024)
- [Pretraining with random noise for uncertainty calibration](https://mlsanity.com/paper/2412.17411/) (2024)
- [Towards Efficient and General-Purpose Few-Shot Misclassification Detection for Vision-Language Models](https://mlsanity.com/paper/2503.20492/) (2025)
- [Sharpness-aware Dynamic Anchor Selection for Generalized Category Discovery](https://mlsanity.com/paper/2512.12925/) (2025)

## Abstract (arXiv)

Reliable confidence estimation for the predictions is important in many safety-critical applications. However, modern deep neural networks are often overconfident for their incorrect predictions. Recently, many calibration methods have been proposed to alleviate the overconfidence problem. With calibrated confidence, a primary and practical purpose is to detect misclassification errors by filtering out low-confidence predictions (known as failure prediction). In this paper, we find a general, widely-existed but actually-neglected phenomenon that most confidence calibration methods are useless or harmful for failure prediction. We investigate this problem and reveal that popular confidence calibration methods often lead to worse confidence separation between correct and incorrect samples, making it more difficult to decide whether to trust a prediction or not. Finally, inspired by the natural connection between flat minima and confidence separation, we propose a simple hypothesis: flat minima is beneficial for failure prediction. We verify this hypothesis via extensive experiments and further boost the performance by combining two different flat minima techniques. Our code is available at https://github.com/Impression2805/FMFP