# Performance Analysis of Out-of-Distribution Detection on Various Trained Neural Networks

arXiv: https://arxiv.org/abs/2103.15580 · HTML: https://mlsanity.com/paper/2103.15580/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 29 references that are in the map.
- First posted on arXiv 29 Mar 2021.

## Builds on (most cited first, 19 of 19)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks](https://mlsanity.com/paper/1706.02690/) (2017)
- [Deep Anomaly Detection with Outlier Exposure](https://mlsanity.com/paper/1812.04606/) (2018)
- [Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks](https://mlsanity.com/paper/1511.04508/) (2015)
- [Towards Open Set Deep Networks](https://mlsanity.com/paper/1511.06233/) (2015)
- [DeepXplore: Automated Whitebox Testing of Deep Learning Systems](https://mlsanity.com/paper/1705.06640/) (2017)
- [NIPS 2016 Tutorial: Generative Adversarial Networks](https://mlsanity.com/paper/1701.00160/) (2016)
- [On Detecting Adversarial Perturbations](https://mlsanity.com/paper/1702.04267/) (2017)
- [Guiding Deep Learning System Testing using Surprise Adequacy](https://mlsanity.com/paper/1808.08444/) (2018)
- [DLFuzz: Differential Fuzzing Testing of Deep Learning Systems](https://mlsanity.com/paper/1808.09413/) (2018)
- [Safely Entering the Deep: A Review of Verification and Validation for Machine Learning and a Challenge Elicitation in the Automotive Industry](https://mlsanity.com/paper/1812.05389/) (2018)
- [An Analysis of ISO 26262: Using Machine Learning Safely in Automotive Software](https://mlsanity.com/paper/1709.02435/) (2017)
- [Towards Structured Evaluation of Deep Neural Network Supervisors](https://mlsanity.com/paper/1903.01263/) (2019)
- [Towards a Framework to Manage Perceptual Uncertainty for Safe Automated Driving](https://mlsanity.com/paper/1903.03438/) (2019)

## Built on by (most cited first, 9 of 9)

- [How to Certify Machine Learning Based Safety-critical Systems? A Systematic Literature Review](https://mlsanity.com/paper/2107.12045/) (2021)
- [Generalization in Neural Networks: A Broad Survey](https://mlsanity.com/paper/2209.01610/) (2022)
- [Generating and Detecting True Ambiguity: A Forgotten Danger in DNN Supervision Testing](https://mlsanity.com/paper/2207.10495/) (2022)
- [Performance Analysis of Out-of-Distribution Detection on Trained Neural Networks](https://mlsanity.com/paper/2204.12378/) (2022)
- [NeuralNEB -- Neural Networks can find Reaction Paths Fast](https://mlsanity.com/paper/2207.09971/) (2022)
- [Uncertainty Quantification for Deep Neural Networks: An Empirical Comparison and Usage Guidelines](https://mlsanity.com/paper/2212.07118/) (2022)
- [Finding Patterns in Ambiguity: Interpretable Stress Testing in the Decision~Boundary](https://mlsanity.com/paper/2408.06302/) (2024)
- [Out-of-Distribution Detection for Safety Assurance of AI and Autonomous Systems](https://mlsanity.com/paper/2510.21254/) (2025)
- [CheapET-3: Cost-Efficient Use of Remote DNN Models](https://mlsanity.com/paper/2208.11552/) (2022)

## Abstract (arXiv)

Several areas have been improved with Deep Learning during the past years. For non-safety related products adoption of AI and ML is not an issue, whereas in safety critical applications, robustness of such approaches is still an issue. A common challenge for Deep Neural Networks (DNN) occur when exposed to out-of-distribution samples that are previously unseen, where DNNs can yield high confidence predictions despite no prior knowledge of the input. In this paper we analyse two supervisors on two well-known DNNs with varied setups of training and find that the outlier detection performance improves with the quality of the training procedure. We analyse the performance of the supervisor after each epoch during the training cycle, to investigate supervisor performance as the accuracy converges. Understanding the relationship between training results and supervisor performance is valuable to improve robustness of the model and indicates where more work has to be done to create generalized models for safety critical applications.