mlsanityData to 14 Oct 2026

Out-of-Distribution Segmentation in Autonomous Driving: Problems and State of the Art

arXiv 2503.08695 ↗First posted 4 Mar 2025cs.CV cs.RO eess.IVcited by 13

Not on the map. Why?

Abstract (arXiv)

In this paper, we review the state of the art in Out-of-Distribution (OoD) segmentation, with a focus on road obstacle detection in automated driving as a real-world application. We analyse the performance of existing methods on two widely used benchmarks, SegmentMeIfYouCan Obstacle Track and LostAndFound-NoKnown, highlighting their strengths, limitations, and real-world applicability. Additionally, we discuss key challenges and outline potential research directions to advance the field. Our goal is to provide researchers and practitioners with a comprehensive perspective on the current landscape of OoD segmentation and to foster further advancements toward safer and more reliable autonomous driving systems.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Builds on 60 of its 74 references that are in the map. First posted on arXiv 4 Mar 2025.

Builds on

60 of 74 references.

References · 60

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  4. 2023Segment Anythingcited by 8,234
  5. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  6. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  7. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  8. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  9. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,223
  10. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  11. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,351
  12. 2016Density estimation using Real NVPcited by 2,042
38 more
  1. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,545
  2. 2017High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANscited by 1,179
  3. 2018Deep Anomaly Detection with Outlier Exposurecited by 942
  4. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 776
  5. 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 453
  6. 2018Do Deep Generative Models Know What They Don't Know?cited by 443
  7. 2019Your Classifier is Secretly an Energy Based Model and You Should Treat it Like Onecited by 405
  8. 2017Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samplescited by 389
  9. 2021Open-Set Recognition: a Good Closed-Set Classifier is All You Need?cited by 353
  10. 2020Why Normalizing Flows Fail to Detect Out-of-Distribution Datacited by 221
  11. 2021SegmentMeIfYouCan: A Benchmark for Anomaly Segmentationcited by 150
  12. 2018Evaluating Bayesian Deep Learning Methods for Semantic Segmentationcited by 143
  13. 2019Detecting the Unexpected via Image Resynthesiscited by 137
  14. 2020Entropy Maximization and Meta Classification for Out-Of-Distribution Detection in Semantic Segmentationcited by 133
  15. 2019The Fishyscapes Benchmark: Measuring Blind Spots in Semantic Segmentationcited by 122
  16. 2016Lost and Found: Detecting Small Road Hazards for Self-Driving Vehiclescited by 117
  17. 2021Pixel-wise Anomaly Detection in Complex Driving Scenescited by 109
  18. 2021Understanding Failures in Out-of-Distribution Detection with Deep Generative Modelscited by 89
  19. 2022GMMSeg: Gaussian Mixture based Generative Semantic Segmentation Modelscited by 87
  20. 2021Pixel-wise Energy-biased Abstention Learning for Anomaly Segmentation on Complex Urban Driving Scenescited by 83
  21. 2024Benchmarking Uncertainty Disentanglement: Specialized Uncertainties for Specialized Taskscited by 78
  22. 2022RbA: Segmenting Unknown Regions Rejected by Allcited by 67
  23. 2018Prediction Error Meta Classification in Semantic Segmentation: Detection via Aggregated Dispersion Measures of Softmax Probabilitiescited by 54
  24. 2023Unmasking Anomalies in Road-Scene Segmentationcited by 45
  25. 2023On Advantages of Mask-level Recognition for Outlier-aware Segmentationcited by 42
  26. 2023Maskomaly:Zero-Shot Mask Anomaly Segmentationcited by 34
  27. 2024Outlier detection by ensembling uncertainty with negative objectnesscited by 34
  28. 2023Strong but simple: A Baseline for Domain Generalized Dense Perception by CLIP-based Transfer Learningcited by 20
  29. 2024PixOOD: Pixel-Level Out-of-Distribution Detectioncited by 20
  30. 2023Perception Datasets for Anomaly Detection in Autonomous Driving: A Surveycited by 16
  31. 2022Far Away in the Deep Space: Dense Nearest-Neighbor-Based Out-of-Distribution Detectioncited by 15
  32. 2023UGainS: Uncertainty Guided Anomaly Instance Segmentationcited by 15
  33. 2023CSL: Class-Agnostic Structure-Constrained Learning for Segmentation Including the Unseencited by 15
  34. 2023ATTA: Anomaly-aware Test-Time Adaptation for Out-of-Distribution Detection in Segmentationcited by 14
  35. 2022Towards Unsupervised Open World Semantic Segmentationcited by 13
  36. 2024A Likelihood Ratio-Based Approach to Segmenting Unknown Objectscited by 12
  37. 2022Knowledge Augmented Machine Learning with Applications in Autonomous Driving: A Surveycited by 11
  38. 2023Pixel-wise Gradient Uncertainty for Convolutional Neural Networks applied to Out-of-Distribution Segmentationcited by 11

50 most cited of 60 All 60 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 8.

13 papers.

Sort:

By area: