# A Data-Driven Measure of Relative Uncertainty for Misclassification Detection

arXiv: https://arxiv.org/abs/2306.01710 · HTML: https://mlsanity.com/paper/2306.01710/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 51 references that are in the map.
- First posted on arXiv 2 Jun 2023.

## Builds on (most cited first, 30 of 39)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [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)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Convex optimization](https://mlsanity.com/paper/2106.01946/) (2021)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks](https://mlsanity.com/paper/1807.03888/) (2018)
- [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)
- [Selective Classification for Deep Neural Networks](https://mlsanity.com/paper/1705.08500/) (2017)
- [A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantification](https://mlsanity.com/paper/2107.07511/) (2021)
- [Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey](https://mlsanity.com/paper/1801.00553/) (2018)
- [Classification with Valid and Adaptive Coverage](https://mlsanity.com/paper/2006.02544/) (2020)
- [Revisiting the Calibration of Modern Neural Networks](https://mlsanity.com/paper/2106.07998/) (2021)
- [Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness](https://mlsanity.com/paper/2006.10108/) (2020)
- [Uncertainty Sets for Image Classifiers using Conformal Prediction](https://mlsanity.com/paper/2009.14193/) (2020)
- [Deep Learning for Anomaly Detection: A Survey](https://mlsanity.com/paper/1901.03407/) (2019)
- [Recent Advances in Open Set Recognition: A Survey](https://mlsanity.com/paper/1811.08581/) (2018)
- [Exploring the Limits of Out-of-Distribution Detection](https://mlsanity.com/paper/2106.03004/) (2021)
- [Mitigating Neural Network Overconfidence with Logit Normalization](https://mlsanity.com/paper/2205.09310/) (2022)
- [A Simple Fix to Mahalanobis Distance for Improving Near-OOD Detection](https://mlsanity.com/paper/2106.09022/) (2021)
- [Deep Deterministic Uncertainty: A Simple Baseline](https://mlsanity.com/paper/2102.11582/) (2021)
- [Addressing Failure Prediction by Learning Model Confidence](https://mlsanity.com/paper/1910.04851/) (2019)
- [Training Uncertainty-Aware Classifiers with Conformalized Deep Learning](https://mlsanity.com/paper/2205.05878/) (2022)
- [DOCTOR: A Simple Method for Detecting Misclassification Errors](https://mlsanity.com/paper/2106.02395/) (2021)
- [Rethinking Confidence Calibration for Failure Prediction](https://mlsanity.com/paper/2303.02970/) (2023)
- [Neural Mean Discrepancy for Efficient Out-of-Distribution Detection](https://mlsanity.com/paper/2104.11408/) (2021)

## Built on by (most cited first, 14 of 14)

- [Uncertainty Quantification with the Empirical Neural Tangent Kernel](https://mlsanity.com/paper/2502.02870/) (2025)
- [ViLU: Learning Vision-Language Uncertainties for Failure Prediction](https://mlsanity.com/paper/2507.07620/) (2025)
- [Online Safety Analysis for LLMs: a Benchmark, an Assessment, and a Path Forward](https://mlsanity.com/paper/2404.08517/) (2024)
- [SwiftLearn: A Data-Efficient Training Method of Deep Learning Models using Importance Sampling](https://mlsanity.com/paper/2311.15134/) (2023)
- [BayesAdapter: enhanced uncertainty estimation in CLIP few-shot adaptation](https://mlsanity.com/paper/2412.09718/) (2024)
- [Beyond the Norms: Detecting Prediction Errors in Regression Models](https://mlsanity.com/paper/2406.06968/) (2024)
- [Multi-Layer Confidence Scoring for Detection of Out-of-Distribution Samples, Adversarial Attacks, and In-Distribution Misclassifications](https://mlsanity.com/paper/2512.19472/) (2025)
- [Is the Last Layer Sufficient for Uncertainty Quantification?](https://mlsanity.com/paper/2605.30741/) (2026)
- [Predicting Probabilities of Error to Combine Quantization and Early Exiting: QuEE](https://mlsanity.com/paper/2406.14404/) (2024)
- [RAT: Boosting Misclassification Detection Ability without Extra Data](https://mlsanity.com/paper/2503.14783/) (2025)
- [X-MAP: eXplainable Misclassification Analysis and Profiling for Spam and Phishing Detection](https://mlsanity.com/paper/2602.15298/) (2026)
- [LogitDynamics: Reliable ViT Error Detection from Layerwise Logit Trajectories](https://mlsanity.com/paper/2604.10643/) (2026)
- [A Convolutional Layer Activation Dimensionality Reduction for Out-of-Distribution and Adversarial Attack Detection Methods](https://mlsanity.com/paper/2608.10203/) (2026)
- [FailSAE: Towards Interpretable Failure Prediction for Vision-Language Models via Sparse Autoencoders](https://mlsanity.com/paper/2609.04276/) (2026)

## Abstract (arXiv)

Misclassification detection is an important problem in machine learning, as it allows for the identification of instances where the model's predictions are unreliable. However, conventional uncertainty measures such as Shannon entropy do not provide an effective way to infer the real uncertainty associated with the model's predictions. In this paper, we introduce a novel data-driven measure of uncertainty relative to an observer for misclassification detection. By learning patterns in the distribution of soft-predictions, our uncertainty measure can identify misclassified samples based on the predicted class probabilities. Interestingly, according to the proposed measure, soft-predictions corresponding to misclassified instances can carry a large amount of uncertainty, even though they may have low Shannon entropy. We demonstrate empirical improvements over multiple image classification tasks, outperforming state-of-the-art misclassification detection methods.