mlsanityData to 14 Oct 2026

Segment Every Out-of-Distribution Object

arXiv 2311.16516 ↗First posted 27 Nov 2023cs.CVcited by 21

Not on the map. Why?

Abstract (arXiv)

Semantic segmentation models, while effective for in-distribution categories, face challenges in real-world deployment due to encountering out-of-distribution (OoD) objects. Detecting these OoD objects is crucial for safety-critical applications. Existing methods rely on anomaly scores, but choosing a suitable threshold for generating masks presents difficulties and can lead to fragmentation and inaccuracy. This paper introduces a method to convert anomaly Score To segmentation Mask, called S2M, a simple and effective framework for OoD detection in semantic segmentation. Unlike assigning anomaly scores to pixels, S2M directly segments the entire OoD object. By transforming anomaly scores into prompts for a promptable segmentation model, S2M eliminates the need for threshold selection. Extensive experiments demonstrate that S2M outperforms the state-of-the-art by approximately 20% in IoU and 40% in mean F1 score, on average, across various benchmarks including Fishyscapes, Segment-Me-If-You-Can, and RoadAnomaly datasets.

Key facts. Cited by 21 papers in the map (data through 14 Oct 2026). Builds on 39 of its 49 references that are in the map. First posted on arXiv 27 Nov 2023.

Builds on

39 of 49 references.

References · 39

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  5. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  6. 2023Segment Anythingcited by 8,234
  7. 2017Mask R-CNNcited by 7,277
  8. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  9. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  10. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  11. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  12. 2020Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformerscited by 1,369
27 more
  1. 2019Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regressioncited by 1,368
  2. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
  3. 2020Energy-based Out-of-distribution Detectioncited by 1,299
  4. 2018Deep Anomaly Detection with Outlier Exposurecited by 942
  5. 2021Segmenter: Transformer for Semantic Segmentationcited by 855
  6. 2021Generalized Out-of-Distribution Detection: A Surveycited by 802
  7. 2021Image Segmentation Using Text and Image Promptscited by 512
  8. 2019Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddingscited by 386
  9. 2019A Survey of Autonomous Driving: Common Practices and Emerging Technologiescited by 379
  10. 2021SegmentMeIfYouCan: A Benchmark for Anomaly Segmentationcited by 150
  11. 2020Autoencoders for Unsupervised Anomaly Segmentation in Brain MR Images: A Comparative Studycited by 147
  12. 2018Evaluating Bayesian Deep Learning Methods for Semantic Segmentationcited by 143
  13. 2020Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts?cited by 139
  14. 2019Detecting the Unexpected via Image Resynthesiscited by 137
  15. 2020Entropy Maximization and Meta Classification for Out-Of-Distribution Detection in Semantic Segmentationcited by 133
  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. 2022Anomaly Detection in Autonomous Driving: A Surveycited by 87
  19. 2021Pixel-wise Energy-biased Abstention Learning for Anomaly Segmentation on Complex Urban Driving Scenescited by 83
  20. 2021Standardized Max Logits: A Simple yet Effective Approach for Identifying Unexpected Road Obstacles in Urban-Scene Segmentationcited by 77
  21. 2022RbA: Segmenting Unknown Regions Rejected by Allcited by 67
  22. 2022Residual Pattern Learning for Pixel-wise Out-of-Distribution Detection in Semantic Segmentationcited by 55
  23. 2020Anomaly detection through latent space restoration using vector-quantized variational autoencoderscited by 45
  24. 2020Out-of-Distribution Detection for Automotive Perceptioncited by 37
  25. 2023ATTA: Anomaly-aware Test-Time Adaptation for Out-of-Distribution Detection in Segmentationcited by 14
  26. 2022N-pad : Neighboring Pixel-based Industrial Anomaly Detectioncited by 11
  27. 2023Redesigning Out-of-Distribution Detection on 3D Medical Imagescited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 11; 2026: 7.

21 papers.

Sort:

By area:

  1. 2024Research on the Application of Computer Vision Based on Deep Learning in Autonomous Driving Technologycited by 9
  2. 2024Finding Dino: A Plug-and-Play Framework for Zero-Shot Detection of Out-of-Distribution Objects Using Prototypescited by 5
  3. 2025Segmenting Objectiveness and Task-awareness Unknown Region for Autonomous Drivingcited by 5
  4. 2025A2Seek: Towards Reasoning-Centric Benchmark for Aerial Anomaly Understandingcited by 5
  5. 2026Open-Vocabulary Domain Generalization in Urban-Scene Segmentationcited by 4
  6. 2024UMAD: Unsupervised Mask-Level Anomaly Detection for Autonomous Drivingcited by 3
  7. 2025Vision Foundation Model Embedding-Based Semantic Anomaly Detectioncited by 3
  8. 2025Uncertainty-Aware Likelihood Ratio Estimation for Pixel-Wise Out-of-Distribution Detectioncited by 3
  9. 2025OoDDINO:A Multi-level Framework for Anomaly Segmentation on Complex Road Scenescited by 2
  10. 2025Open-set Anomaly Segmentation in Complex Scenarioscited by 1
  11. 2025Leveraging Text-Driven Semantic Variation for Robust OOD Segmentationcited by 1
  12. 2026Mitigating the ID-OOD Tradeoff in Open-Set Test-Time Adaptationcited by 1
9 more
  1. 2025CoT-Segmenter: Enhancing OOD Detection in Dense Road Scenes via Chain-of-Thought Reasoningcited by 0
  2. 2025Objectomaly: Objectness-Aware Refinement for OoD Segmentation with Structural Consistency and Boundary Precisioncited by 0
  3. 2025Distributional Uncertainty for Out-of-Distribution Detectioncited by 0
  4. 2025ClimaOoD: Improving Anomaly Segmentation via Physically Realistic Synthetic Datacited by 0
  5. 2026Toxicity Assessment in Preclinical Histopathology via Class-Aware Mahalanobis Distance for Known and Novel Anomaliescited by 0
  6. 2026Out-of-Distribution Object Detection in Street Scenes via Synthetic Outlier Exposure and Transfer Learningcited by 0
  7. 2026CURE-OOD: Benchmarking Out-of-Distribution Detection for Survival Predictioncited by 0
  8. 2026LARAD: Layout-Aware Road Anomaly Detection via Spatial-Logic Reasoningcited by 0
  9. 2026Towards Real-Time PixOOD: Efficient Anomaly Segmentation for Autonomous Vehiclescited by 0