mlsanityData to 7 Oct 2026

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

arXiv 2212.07773 ↗First posted 15 Dec 2022cs.LGcited by 7

Not on the map. Why?

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.

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

Builds on

24 of 35 references.

References · 24

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  3. 2017Squeeze-and-Excitation Networkscited by 4,763
  4. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  5. 2018YOLOv3: An Incremental Improvementcited by 2,652
  6. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  7. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  8. 2019Scaling Out-of-Distribution Detection for Real-World Settingscited by 465
  9. 2018Efficient Neural Network Robustness Certification with General Activation Functionscited by 439
  10. 2019Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Comingcited by 332
  11. 2022VOS: Learning What You Don't Know by Virtual Outlier Synthesiscited by 300
  12. 2020A2D2: Audi Autonomous Driving Datasetcited by 189
12 more
  1. 2017A Study and Comparison of Human and Deep Learning Recognition Performance Under Visual Distortionscited by 107
  2. 2021Can multi-label classification networks know what they don't know?cited by 100
  3. 2017Universal Adversarial Perturbations Against Semantic Image Segmentationcited by 92
  4. 2021The Second International Verification of Neural Networks Competition (VNN-COMP 2021): Summary and Resultscited by 71
  5. 2022Unknown-Aware Object Detection: Learning What You Don't Know from Videos in the Wildcited by 70
  6. 2017Google's Cloud Vision API Is Not Robust To Noisecited by 37
  7. 2019Outside the Box: Abstraction-Based Monitoring of Neural Networkscited by 36
  8. 2018Runtime Monitoring Neuron Activation Patternscited by 34
  9. 2020Poly-YOLO: higher speed, more precise detection and instance segmentation for YOLOv3cited by 22
  10. 2020Into the Unknown: Active Monitoring of Neural Networkscited by 19
  11. 2019Towards Safety Verification of Direct Perception Neural Networkscited by 9
  12. 2020Provably-Robust Runtime Monitoring of Neuron Activation Patternscited by 9

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 4; 2025: 2.

7 papers.

  1. 2025Handling Out-of-Distribution Data: A Surveycited by 14
  2. 2023Verifying Generalization in Deep Learningcited by 11
  3. 2024Towards Formal Verification of Deep Neural Networks for Object Detectioncited by 4
  4. 2024Monitizer: Automating Design and Evaluation of Neural Network Monitorscited by 2
  5. 2024Edge Case Detection in Automated Driving: Methods, Challenges, and Future Directionscited by 2
  6. 2025Runtime Safety Monitoring of Deep Neural Networks for Perception: A Surveycited by 2
  7. 2024Learning Run-time Safety Monitors for Machine Learning Componentscited by 0