# Enhancing Deep Neural Network Reliability with Refinement and Calibration

arXiv: https://arxiv.org/abs/2605.23249 · HTML: https://mlsanity.com/paper/2605.23249/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 31 of its 48 references that are in the map.
- First posted on arXiv 22 May 2026.

## Builds on (most cited first, 30 of 31)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [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)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks](https://mlsanity.com/paper/1706.02690/) (2017)
- [Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss](https://mlsanity.com/paper/1906.07413/) (2019)
- [When Does Label Smoothing Help?](https://mlsanity.com/paper/1906.02629/) (2019)
- [Large-Scale Long-Tailed Recognition in an Open World](https://mlsanity.com/paper/1904.05160/) (2019)
- [Measuring Calibration in Deep Learning](https://mlsanity.com/paper/1904.01685/) (2019)
- [Revisiting the Calibration of Modern Neural Networks](https://mlsanity.com/paper/2106.07998/) (2021)
- [Beyond temperature scaling: Obtaining well-calibrated multiclass probabilities with Dirichlet calibration](https://mlsanity.com/paper/1910.12656/) (2019)
- [Verified Uncertainty Calibration](https://mlsanity.com/paper/1909.10155/) (2019)
- [On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networks](https://mlsanity.com/paper/1905.11001/) (2019)
- [Mitigating Neural Network Overconfidence with Logit Normalization](https://mlsanity.com/paper/2205.09310/) (2022)
- [Confidence-Aware Learning for Deep Neural Networks](https://mlsanity.com/paper/2007.01458/) (2020)
- [AUC Maximization in the Era of Big Data and AI: A Survey](https://mlsanity.com/paper/2203.15046/) (2022)
- [Local Temperature Scaling for Probability Calibration](https://mlsanity.com/paper/2008.05105/) (2020)
- [The Devil is in the Margin: Margin-based Label Smoothing for Network Calibration](https://mlsanity.com/paper/2111.15430/) (2021)
- [Large-scale Robust Deep AUC Maximization: A New Surrogate Loss and Empirical Studies on Medical Image Classification](https://mlsanity.com/paper/2012.03173/) (2020)
- [Better Uncertainty Calibration via Proper Scores for Classification and Beyond](https://mlsanity.com/paper/2203.07835/) (2022)
- [A Unifying Theory of Distance from Calibration](https://mlsanity.com/paper/2211.16886/) (2022)
- [A Stitch in Time Saves Nine: A Train-Time Regularizing Loss for Improved Neural Network Calibration](https://mlsanity.com/paper/2203.13834/) (2022)
- [Learning with Multiclass AUC: Theory and Algorithms](https://mlsanity.com/paper/2107.13171/) (2021)
- [AdaFocal: Calibration-aware Adaptive Focal Loss](https://mlsanity.com/paper/2211.11838/) (2022)
- [Calibrating Deep Neural Networks using Explicit Regularisation and Dynamic Data Pruning](https://mlsanity.com/paper/2212.10005/) (2022)
- [Optimizing Two-way Partial AUC with an End-to-end Framework](https://mlsanity.com/paper/2206.11655/) (2022)
- [PnPOOD : Out-Of-Distribution Detection for Text Classification via Plug andPlay Data Augmentation](https://mlsanity.com/paper/2111.00506/) (2021)
- [A Novel Data Augmentation Technique for Out-of-Distribution Sample Detection using Compounded Corruptions](https://mlsanity.com/paper/2207.13916/) (2022)

## Abstract (arXiv)

Although deep neural networks (DNNs) achieve high predictive accuracy, their confidence estimates are often unreliable, potentially compromising user trust in their decisions. This has motivated research on calibrated models, where calibration measures how well a model's predicted confidence aligns with the empirical probability of correctness. However, calibration metrics can often be improved through post-processing techniques that merely mimic training-time uncertainty without genuinely improving the model's understanding. For this reason, statisticians recommend that models be not only calibrated but also refined. Intuitively, a model is considered more refined if it assigns significantly different confidence scores to correct and incorrect predictions, a property also referred to as sharpness. We observe that many existing calibration methods improve calibration at the cost of reduced refinement. To address this limitation, we propose: (1) a novel loss function that explicitly promotes refinement and can be optimized through supervised contrastive learning; and (2) a unified training framework, RefCal, that jointly optimizes calibration, refinement, and accuracy to improve DNN reliability. On the CIFAR-100-LT dataset with 10 percent class imbalance, RefCal achieves (accuracy, refinement, ECE) of (58.81, 95.67, 0.08), substantially outperforming the widely used Correctness Ranking Loss, which achieves (46.27, 93.7, 0.22).