# Runtime Monitoring for Out-of-Distribution Detection in Object Detection Neural Networks

arXiv: https://arxiv.org/abs/2212.07773 · HTML: https://mlsanity.com/paper/2212.07773/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 35 references that are in the map.
- First posted on arXiv 15 Dec 2022.

## Builds on (most cited first, 24 of 24)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks](https://mlsanity.com/paper/1706.02690/) (2017)
- [Generalized Out-of-Distribution Detection: A Survey](https://mlsanity.com/paper/2110.11334/) (2021)
- [Scaling Out-of-Distribution Detection for Real-World Settings](https://mlsanity.com/paper/1911.11132/) (2019)
- [Efficient Neural Network Robustness Certification with General Activation Functions](https://mlsanity.com/paper/1811.00866/) (2018)
- [Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming](https://mlsanity.com/paper/1907.07484/) (2019)
- [VOS: Learning What You Don't Know by Virtual Outlier Synthesis](https://mlsanity.com/paper/2202.01197/) (2022)
- [A2D2: Audi Autonomous Driving Dataset](https://mlsanity.com/paper/2004.06320/) (2020)
- [A Study and Comparison of Human and Deep Learning Recognition Performance Under Visual Distortions](https://mlsanity.com/paper/1705.02498/) (2017)
- [Can multi-label classification networks know what they don't know?](https://mlsanity.com/paper/2109.14162/) (2021)
- [Universal Adversarial Perturbations Against Semantic Image Segmentation](https://mlsanity.com/paper/1704.05712/) (2017)
- [The Second International Verification of Neural Networks Competition (VNN-COMP 2021): Summary and Results](https://mlsanity.com/paper/2109.00498/) (2021)
- [Unknown-Aware Object Detection: Learning What You Don't Know from Videos in the Wild](https://mlsanity.com/paper/2203.03800/) (2022)
- [Google's Cloud Vision API Is Not Robust To Noise](https://mlsanity.com/paper/1704.05051/) (2017)
- [Outside the Box: Abstraction-Based Monitoring of Neural Networks](https://mlsanity.com/paper/1911.09032/) (2019)
- [Runtime Monitoring Neuron Activation Patterns](https://mlsanity.com/paper/1809.06573/) (2018)
- [Poly-YOLO: higher speed, more precise detection and instance segmentation for YOLOv3](https://mlsanity.com/paper/2005.13243/) (2020)
- [Into the Unknown: Active Monitoring of Neural Networks](https://mlsanity.com/paper/2009.06429/) (2020)
- [Towards Safety Verification of Direct Perception Neural Networks](https://mlsanity.com/paper/1904.04706/) (2019)
- [Provably-Robust Runtime Monitoring of Neuron Activation Patterns](https://mlsanity.com/paper/2011.11959/) (2020)

## Built on by (most cited first, 7 of 7)

- [Handling Out-of-Distribution Data: A Survey](https://mlsanity.com/paper/2507.21160/) (2025)
- [Verifying Generalization in Deep Learning](https://mlsanity.com/paper/2302.05745/) (2023)
- [Towards Formal Verification of Deep Neural Networks for Object Detection](https://mlsanity.com/paper/2407.01295/) (2024)
- [Monitizer: Automating Design and Evaluation of Neural Network Monitors](https://mlsanity.com/paper/2405.10350/) (2024)
- [Edge Case Detection in Automated Driving: Methods, Challenges, and Future Directions](https://mlsanity.com/paper/2410.08491/) (2024)
- [Runtime Safety Monitoring of Deep Neural Networks for Perception: A Survey](https://mlsanity.com/paper/2511.05982/) (2025)
- [Learning Run-time Safety Monitors for Machine Learning Components](https://mlsanity.com/paper/2406.16220/) (2024)

## Abstract (arXiv)

Runtime monitoring provides a more realistic and applicable alternative to verification in the setting of real neural networks used in industry. It is particularly useful for detecting out-of-distribution (OOD) inputs, for which the network was not trained and can yield erroneous results. We extend a runtime-monitoring approach previously proposed for classification networks to perception systems capable of identification and localization of multiple objects. Furthermore, we analyze its adequacy experimentally on different kinds of OOD settings, documenting the overall efficacy of our approach.