mlsanityData to 14 Oct 2026

Out-of-Distribution Detection for Automotive Perception

arXiv 2011.01413 ↗First posted 3 Nov 2020cs.CV cs.ROcited by 37

Not on the map. Why?

Abstract (arXiv)

Neural networks (NNs) are widely used for object classification in autonomous driving. However, NNs can fail on input data not well represented by the training dataset, known as out-of-distribution (OOD) data. A mechanism to detect OOD samples is important for safety-critical applications, such as automotive perception, to trigger a safe fallback mode. NNs often rely on softmax normalization for confidence estimation, which can lead to high confidences being assigned to OOD samples, thus hindering the detection of failures. This paper presents a method for determining whether inputs are OOD, which does not require OOD data during training and does not increase the computational cost of inference. The latter property is especially important in automotive applications with limited computational resources and real-time constraints. Our proposed approach outperforms state-of-the-art methods on real-world automotive datasets.

Key facts. Cited by 37 papers in the map (data through 14 Oct 2026). First posted on arXiv 3 Nov 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 2; 2022: 10; 2023: 6; 2024: 11; 2025: 6; 2026: 2.

37 papers.

Sort:

By area:

  1. 2025SAFE: Multitask Failure Detection for Vision-Language-Action Modelscited by 80
  2. 2022Disentangling Epistemic and Aleatoric Uncertainty in Reinforcement Learningcited by 27
  3. 2022Interpretable Self-Aware Neural Networks for Robust Trajectory Predictioncited by 22
  4. 2023Segment Every Out-of-Distribution Objectcited by 21
  5. 2022How Do We Fail? Stress Testing Perception in Autonomous Vehiclescited by 18
  6. 2022Out-of-Distribution Detection for LiDAR-based 3D Object Detectioncited by 17
  7. 2022Correct-by-Construction Runtime Enforcement in AI -- A Surveycited by 12
  8. 2024The Role of Predictive Uncertainty and Diversity in Embodied AI and Robot Learningcited by 11
  9. 2024Failures Are Fated, But Can Be Faded: Characterizing and Mitigating Unwanted Behaviors in Large-Scale Vision and Language Modelscited by 11
  10. 2021Out of Distribution Detection and Adversarial Attacks on Deep Neural Networks for Robust Medical Image Analysiscited by 10
  11. 2024Generating Out-Of-Distribution Scenarios Using Language Modelscited by 10
  12. 2021Improving Variational Autoencoder based Out-of-Distribution Detection for Embedded Real-time Applicationscited by 9
25 more
  1. 2023Projection Regret: Reducing Background Bias for Novelty Detection via Diffusion Modelscited by 9
  2. 2023Topology-Matching Normalizing Flows for Out-of-Distribution Detection in Robot Learningcited by 7
  3. 2024A Unified Approach Towards Active Learning and Out-of-Distribution Detectioncited by 7
  4. 2024RoboMD: Uncovering Robot Vulnerabilities through Semantic Potential Fieldscited by 7
  5. 2024Out-of-Distribution Data: An Acquaintance of Adversarial Examples -- A Surveycited by 6
  6. 2022A Comprehensive Review of Trends, Applications and Challenges In Out-of-Distribution Detectioncited by 5
  7. 2022Multimodal Detection of Unknown Objects on Roads for Autonomous Drivingcited by 4
  8. 2022Topological Structure Learning for Weakly-Supervised Out-of-Distribution Detectioncited by 4
  9. 2024PLoc: A New Evaluation Criterion Based on Physical Location for Autonomous Driving Datasetscited by 4
  10. 2025RUNA: Object-level Out-of-Distribution Detection via Regional Uncertainty Alignment of Multimodal Representationscited by 4
  11. 2022Conquering Ghosts: Relation Learning for Information Reliability Representation and End-to-End Robust Navigationcited by 3
  12. 2023Out of Distribution Detection via Domain-Informed Gaussian Process State Space Modelscited by 3
  13. 2022Experiments on Anomaly Detection in Autonomous Driving by Forward-Backward Style Transferscited by 1
  14. 2023Conditioning Latent-Space Clusters for Real-World Anomaly Classificationcited by 1
  15. 2023ExCeL : Combined Extreme and Collective Logit Information for Enhancing Out-of-Distribution Detectioncited by 1
  16. 2024From COCO to COCO-FP: A Deep Dive into Background False Positives for COCO Detectorscited by 1
  17. 2024Multimodal-Enhanced Objectness Learner for Corner Case Detection in Autonomous Drivingcited by 0
  18. 2024Criteria for Uncertainty-based Corner Cases Detection in Instance Segmentationcited by 0
  19. 2024LLM-Assisted Red Teaming of Diffusion Models through "Failures Are Fated, But Can Be Faded"cited by 0
  20. 2025VisTa: Visual-contextual and Text-augmented Zero-shot Object-level OOD Detectioncited by 0
  21. 2025FindMeIfYouCan: Bringing Open Set metrics to textitnear , textitfar and textitfarther Out-of-Distribution Object Detectioncited by 0
  22. 2025Exploiting Vision Language Model for Training-Free 3D Point Cloud OOD Detection via Graph Score Propagationcited by 0
  23. 2025Adaptive Multi-Mode Out-of-Distribution Detection for Trajectory Prediction in Autonomous Vehiclescited by 0
  24. 2026SeNeDiF-OOD: Semantic Nested Dichotomy Fusion for Out-of-Distribution Detection Methodology in Open-World Classification. A Case Study on Monument Style Classificationcited by 0
  25. 2026VOLTA: The Surprising Ineffectiveness of Auxiliary Losses for Calibrated Deep Learningcited by 0