# Distance-based Confidence Score for Neural Network Classifiers

arXiv: https://arxiv.org/abs/1709.09844 · HTML: https://mlsanity.com/paper/1709.09844/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Sep 2017.

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

- [Revisiting Mahalanobis Distance for Transformer-Based Out-of-Domain Detection](https://mlsanity.com/paper/2101.03778/) (2021)
- [On the Practicality of Deterministic Epistemic Uncertainty](https://mlsanity.com/paper/2107.00649/) (2021)
- [Confidence Score for Source-Free Unsupervised Domain Adaptation](https://mlsanity.com/paper/2206.06640/) (2022)
- [Is Fine-tuning Needed? Pre-trained Language Models Are Near Perfect for Out-of-Domain Detection](https://mlsanity.com/paper/2305.13282/) (2023)
- [Noise-resistant Deep Metric Learning with Ranking-based Instance Selection](https://mlsanity.com/paper/2103.16047/) (2021)
- [GOLD: Improving Out-of-Scope Detection in Dialogues using Data Augmentation](https://mlsanity.com/paper/2109.03079/) (2021)
- [A Comprehensive Review of Digital Twin -- Part 2: Roles of Uncertainty Quantification and Optimization, a Battery Digital Twin, and Perspectives](https://mlsanity.com/paper/2208.12904/) (2022)
- [Latent Discriminant deterministic Uncertainty](https://mlsanity.com/paper/2207.10130/) (2022)
- [Out of Distribution Data Detection Using Dropout Bayesian Neural Networks](https://mlsanity.com/paper/2202.08985/) (2022)
- [An Informative Path Planning Framework for Active Learning in UAV-based Semantic Mapping](https://mlsanity.com/paper/2302.03347/) (2023)
- [Confidence Estimation Using Unlabeled Data](https://mlsanity.com/paper/2307.10440/) (2023)
- [Explainable Artificial Intelligence (XAI) for Increasing User Trust in Deep Reinforcement Learning Driven Autonomous Systems](https://mlsanity.com/paper/2106.03775/) (2021)
- [Using Neural Networks for Novelty-based Test Selection to Accelerate Functional Coverage Closure](https://mlsanity.com/paper/2207.00445/) (2022)
- [Auditing AI models for Verified Deployment under Semantic Specifications](https://mlsanity.com/paper/2109.12456/) (2021)
- [ORCE: Order-Aware Alignment of Verbalized Confidence in Large Language Models](https://mlsanity.com/paper/2605.12446/) (2026)
- [Out-of-Distribution Example Detection in Deep Neural Networks using Distance to Modelled Embedding](https://mlsanity.com/paper/2108.10673/) (2021)
- [HYCEDIS: HYbrid Confidence Engine for Deep Document Intelligence System](https://mlsanity.com/paper/2206.02628/) (2022)
- [Assorted, Archetypal and Annotated Two Million (3A2M) Cooking Recipes Dataset based on Active Learning](https://mlsanity.com/paper/2303.16778/) (2023)
- [Discriminant Distance-Aware Representation on Deterministic Uncertainty Quantification Methods](https://mlsanity.com/paper/2402.12664/) (2024)
- [Towards Trustworthy Vital Sign Forecasting: Leveraging Uncertainty for Prediction Intervals](https://mlsanity.com/paper/2509.01319/) (2025)
- [DIRA: Dynamic Domain Incremental Regularised Adaptation](https://mlsanity.com/paper/2205.00147/) (2022)
- [Exploring the Potential of Bilevel Optimization for Calibrating Neural Networks](https://mlsanity.com/paper/2503.13113/) (2025)
- [SupLID: Geometrical Guidance for Out-of-Distribution Detection in Semantic Segmentation](https://mlsanity.com/paper/2511.18816/) (2025)
- [A Multiple Classifier Approach for Concatenate-Designed Neural Networks](https://mlsanity.com/paper/2101.05457/) (2021)
- [Hack The Box: Fooling Deep Learning Abstraction-Based Monitors](https://mlsanity.com/paper/2107.04764/) (2021)
- [Noise-Resistant Deep Metric Learning with Probabilistic Instance Filtering](https://mlsanity.com/paper/2108.01431/) (2021)
- [CBGT-Net: A Neuromimetic Architecture for Robust Classification of Streaming Data](https://mlsanity.com/paper/2403.15974/) (2024)
- [Sparse Domain Transfer via Elastic Net Regularization](https://mlsanity.com/paper/2405.07489/) (2024)
- [Robust quantum dots charge autotuning using neural network uncertainty](https://mlsanity.com/paper/2406.05175/) (2024)
- [OT Score: An OT based Confidence Score for Prototype-Assisted Source Free Unsupervised Domain Adaptation](https://mlsanity.com/paper/2505.11669/) (2025)

## Abstract (arXiv)

The reliable measurement of confidence in classifiers' predictions is very important for many applications and is, therefore, an important part of classifier design. Yet, although deep learning has received tremendous attention in recent years, not much progress has been made in quantifying the prediction confidence of neural network classifiers. Bayesian models offer a mathematically grounded framework to reason about model uncertainty, but usually come with prohibitive computational costs. In this paper we propose a simple, scalable method to achieve a reliable confidence score, based on the data embedding derived from the penultimate layer of the network. We investigate two ways to achieve desirable embeddings, by using either a distance-based loss or Adversarial Training. We then test the benefits of our method when used for classification error prediction, weighting an ensemble of classifiers, and novelty detection. In all tasks we show significant improvement over traditional, commonly used confidence scores.