# Bias-Reduced Uncertainty Estimation for Deep Neural Classifiers

arXiv: https://arxiv.org/abs/1805.08206 · HTML: https://mlsanity.com/paper/1805.08206/

## Key facts

- Cited by 113 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 May 2018.

## Built on by (most cited first, 30 of 113)

- [Entropy is not Enough for Test-Time Adaptation: From the Perspective of Disentangled Factors](https://mlsanity.com/paper/2403.07366/) (2024)
- [Provable Dynamic Fusion for Low-Quality Multimodal Data](https://mlsanity.com/paper/2306.02050/) (2023)
- [Differentiable Learning Under Triage](https://mlsanity.com/paper/2103.08902/) (2021)
- [Conditional-Flow NeRF: Accurate 3D Modelling with Reliable Uncertainty Quantification](https://mlsanity.com/paper/2203.10192/) (2022)
- [Confidence Score for Source-Free Unsupervised Domain Adaptation](https://mlsanity.com/paper/2206.06640/) (2022)
- [DOCTOR: A Simple Method for Detecting Misclassification Errors](https://mlsanity.com/paper/2106.02395/) (2021)
- [A Call to Reflect on Evaluation Practices for Failure Detection in Image Classification](https://mlsanity.com/paper/2211.15259/) (2022)
- [Rethinking Confidence Calibration for Failure Prediction](https://mlsanity.com/paper/2303.02970/) (2023)
- [Overcoming Common Flaws in the Evaluation of Selective Classification Systems](https://mlsanity.com/paper/2407.01032/) (2024)
- [What Can We Learn From The Selective Prediction And Uncertainty Estimation Performance Of 523 Imagenet Classifiers](https://mlsanity.com/paper/2302.11874/) (2023)
- [UMIX: Improving Importance Weighting for Subpopulation Shift via Uncertainty-Aware Mixup](https://mlsanity.com/paper/2209.08928/) (2022)
- [Smaller Language Models are capable of selecting Instruction-Tuning Training Data for Larger Language Models](https://mlsanity.com/paper/2402.10430/) (2024)
- [Augmenting Softmax Information for Selective Classification with Out-of-Distribution Data](https://mlsanity.com/paper/2207.07506/) (2022)
- [ValUES: A Framework for Systematic Validation of Uncertainty Estimation in Semantic Segmentation](https://mlsanity.com/paper/2401.08501/) (2024)
- [Calibrating Uncertainty for Semi-Supervised Crowd Counting](https://mlsanity.com/paper/2308.09887/) (2023)
- [Selective Prediction via Training Dynamics](https://mlsanity.com/paper/2205.13532/) (2022)
- [Efficient Out-of-Distribution Detection Using Latent Space of β-VAE for Cyber-Physical Systems](https://mlsanity.com/paper/2108.11800/) (2021)
- [Disrupting Deep Uncertainty Estimation Without Harming Accuracy](https://mlsanity.com/paper/2110.13741/) (2021)
- [A Unified Benchmark for the Unknown Detection Capability of Deep Neural Networks](https://mlsanity.com/paper/2112.00337/) (2021)
- [Respecting Transfer Gap in Knowledge Distillation](https://mlsanity.com/paper/2210.12787/) (2022)
- [The Devil is in the Wrongly-classified Samples: Towards Unified Open-set Recognition](https://mlsanity.com/paper/2302.04002/) (2023)
- [Window-Based Early-Exit Cascades for Uncertainty Estimation: When Deep Ensembles are More Efficient than Single Models](https://mlsanity.com/paper/2303.08010/) (2023)
- [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)
- [Reinforcement Learning Under Algorithmic Triage](https://mlsanity.com/paper/2109.11328/) (2021)
- [A Novel Characterization of the Population Area Under the Risk Coverage Curve (AURC) and Rates of Finite Sample Estimators](https://mlsanity.com/paper/2410.15361/) (2024)
- [Average of Pruning: Improving Performance and Stability of Out-of-Distribution Detection](https://mlsanity.com/paper/2303.01201/) (2023)
- [Selective Classification Under Distribution Shifts](https://mlsanity.com/paper/2405.05160/) (2024)
- [LOPS: Learning Order Inspired Pseudo-Label Selection for Weakly Supervised Text Classification](https://mlsanity.com/paper/2205.12528/) (2022)
- [Towards Understanding Why Label Smoothing Degrades Selective Classification and How to Fix It](https://mlsanity.com/paper/2403.14715/) (2024)
- [Temporal Knowledge Sharing enable Spiking Neural Network Learning from Past and Future](https://mlsanity.com/paper/2304.06540/) (2023)

## Abstract (arXiv)

We consider the problem of uncertainty estimation in the context of (non-Bayesian) deep neural classification. In this context, all known methods are based on extracting uncertainty signals from a trained network optimized to solve the classification problem at hand. We demonstrate that such techniques tend to introduce biased estimates for instances whose predictions are supposed to be highly confident. We argue that this deficiency is an artifact of the dynamics of training with SGD-like optimizers, and it has some properties similar to overfitting. Based on this observation, we develop an uncertainty estimation algorithm that selectively estimates the uncertainty of highly confident points, using earlier snapshots of the trained model, before their estimates are jittered (and way before they are ready for actual classification). We present extensive experiments indicating that the proposed algorithm provides uncertainty estimates that are consistently better than all known methods.