mlsanityData to 14 Oct 2026

Concurrent Misclassification and Out-of-Distribution Detection for Semantic Segmentation via Energy-Based Normalizing Flow

arXiv 2305.09610 ↗First posted 16 May 2023cs.CV cs.AI cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

Recent semantic segmentation models accurately classify test-time examples that are similar to a training dataset distribution. However, their discriminative closed-set approach is not robust in practical data setups with distributional shifts and out-of-distribution (OOD) classes. As a result, the predicted probabilities can be very imprecise when used as confidence scores at test time. To address this, we propose a generative model for concurrent in-distribution misclassification (IDM) and OOD detection that relies on a normalizing flow framework. The proposed flow-based detector with an energy-based inputs (FlowEneDet) can extend previously deployed segmentation models without their time-consuming retraining. Our FlowEneDet results in a low-complexity architecture with marginal increase in the memory footprint. FlowEneDet achieves promising results on Cityscapes, Cityscapes-C, FishyScapes and SegmentMeIfYouCan benchmarks in IDM/OOD detection when applied to pretrained DeepLabV3+ and SegFormer semantic segmentation models.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 44 of its 53 references that are in the map. First posted on arXiv 16 May 2023.

Builds on

44 of 53 references.

References · 44

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  3. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,223
  4. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,940
  5. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  6. 2015Variational Inference with Normalizing Flowscited by 2,170
  7. 2016Density estimation using Real NVPcited by 2,042
  8. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,545
  9. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  10. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
  11. 2020Energy-based Out-of-distribution Detectioncited by 1,299
  12. 2017Masked Autoregressive Flow for Density Estimationcited by 684
32 more
  1. 2020RobustBench: a standardized adversarial robustness benchmarkcited by 661
  2. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 531
  3. 2019Scaling Out-of-Distribution Detection for Real-World Settingscited by 465
  4. 2018Do Deep Generative Models Know What They Don't Know?cited by 443
  5. 2019Your Classifier is Secretly an Energy Based Model and You Should Treat it Like Onecited by 405
  6. 2019Beyond temperature scaling: Obtaining well-calibrated multiclass probabilities with Dirichlet calibrationcited by 364
  7. 2019Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Comingcited by 336
  8. 2022VOS: Learning What You Don't Know by Virtual Outlier Synthesiscited by 300
  9. 2021Unsolved Problems in ML Safetycited by 292
  10. 2022Extremely Simple Activation Shaping for Out-of-Distribution Detectioncited by 212
  11. 2021SegmentMeIfYouCan: A Benchmark for Anomaly Segmentationcited by 150
  12. 2019Guided Image Generation with Conditional Invertible Neural Networkscited by 147
  13. 2018Deep Autoencoding Models for Unsupervised Anomaly Segmentation in Brain MR Imagescited by 146
  14. 2022Understanding The Robustness in Vision Transformerscited by 144
  15. 2018Evaluating Bayesian Deep Learning Methods for Semantic Segmentationcited by 143
  16. 2019Detecting the Unexpected via Image Resynthesiscited by 137
  17. 2020Entropy Maximization and Meta Classification for Out-Of-Distribution Detection in Semantic Segmentationcited by 133
  18. 2021Pixel-wise Anomaly Detection in Complex Driving Scenescited by 109
  19. 2020Synthesize then Compare: Detecting Failures and Anomalies for Semantic Segmentationcited by 96
  20. 2022GMMSeg: Gaussian Mixture based Generative Semantic Segmentation Modelscited by 87
  21. 2021Pixel-wise Energy-biased Abstention Learning for Anomaly Segmentation on Complex Urban Driving Scenescited by 83
  22. 2021Provable Guarantees for Understanding Out-of-distribution Detectioncited by 78
  23. 2021Standardized Max Logits: A Simple yet Effective Approach for Identifying Unexpected Road Obstacles in Urban-Scene Segmentationcited by 77
  24. 2019Sampling-free Epistemic Uncertainty Estimation Using Approximated Variance Propagationcited by 74
  25. 2019Simultaneous Semantic Segmentation and Outlier Detection in Presence of Domain Shiftcited by 54
  26. 2023Out-of-distribution Detection with Implicit Outlier Transformationcited by 43
  27. 2019Hybrid Models with Deep and Invertible Featurescited by 41
  28. 2021Triggering Failures: Out-Of-Distribution detection by learning from local adversarial attacks in Semantic Segmentationcited by 40
  29. 2020Deep Active Learning for Biased Datasets via Fisher Kernel Self-Supervisioncited by 32
  30. 2020Why is the Mahalanobis Distance Effective for Anomaly Detection?cited by 28
  31. 2019Density estimation in representation space to predict model uncertaintycited by 27
  32. 2021Generative Flows with Invertible Attentionscited by 13

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 3; 2026: 2.

8 papers.

  1. 2025Out-of-Distribution Segmentation in Autonomous Driving: Problems and State of the Artcited by 13
  2. 2024ContextFlow++: Generalist-Specialist Flow-based Generative Models with Mixed-Variable Context Encodingcited by 3
  3. 2024Multi-Scale Foreground-Background Confidence for Out-of-Distribution Segmentationcited by 3
  4. 2024FlowCLAS: Enhancing Normalizing Flow Via Contrastive Learning For Anomaly Segmentationcited by 2
  5. 2025Anomalies by Synthesis: Anomaly Detection using Generative Diffusion Models for Off-Road Navigationcited by 2
  6. 2025Distributional Uncertainty for Out-of-Distribution Detectioncited by 0
  7. 2026Combining Foundation Model Confidence and Monocular Depth for Training-Free Out-of-Distribution Segmentationcited by 0
  8. 2026SAFe: Segment-guided Aggregation of Feature Densities for Anomaly-aware Segmentationcited by 0