mlsanityData to 7 Oct 2026

Triggering Failures: Out-Of-Distribution detection by learning from local adversarial attacks in Semantic Segmentation

arXiv 2108.01634 ↗First posted 3 Aug 2021cs.CVcited by 40

Not on the map. Why?

Abstract (arXiv)

In this paper, we tackle the detection of out-of-distribution (OOD) objects in semantic segmentation. By analyzing the literature, we found that current methods are either accurate or fast but not both which limits their usability in real world applications. To get the best of both aspects, we propose to mitigate the common shortcomings by following four design principles: decoupling the OOD detection from the segmentation task, observing the entire segmentation network instead of just its output, generating training data for the OOD detector by leveraging blind spots in the segmentation network and focusing the generated data on localized regions in the image to simulate OOD objects. Our main contribution is a new OOD detection architecture called ObsNet associated with a dedicated training scheme based on Local Adversarial Attacks (LAA). We validate the soundness of our approach across numerous ablation studies. We also show it obtains top performances both in speed and accuracy when compared to ten recent methods of the literature on three different datasets.

Key facts. Cited by 40 papers in the map (data through 7 Oct 2026). Builds on 47 of its 69 references that are in the map. First posted on arXiv 3 Aug 2021.

Builds on

47 of 69 references.

References · 47

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2017Mask R-CNNcited by 7,259
  5. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  6. 2017On Calibration of Modern Neural Networkscited by 4,860
  7. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  8. 2014Going Deeper with Convolutionscited by 4,231
  9. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  10. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  11. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  12. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
35 more
  1. 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,483
  2. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  3. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  4. 2018BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learningcited by 1,282
  5. 2018Deep Anomaly Detection with Outlier Exposurecited by 939
  6. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 918
  7. 2018Robustness May Be at Odds with Accuracycited by 873
  8. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
  9. 2018Evidential Deep Learning to Quantify Classification Uncertaintycited by 728
  10. 2017Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoverycited by 566
  11. 2018Predictive Uncertainty Estimation via Prior Networkscited by 555
  12. 2019A Simple Baseline for Bayesian Uncertainty in Deep Learningcited by 555
  13. 2015Weight Uncertainty in Neural Networkscited by 554
  14. 2019Measuring Calibration in Deep Learningcited by 443
  15. 2019Using Pre-Training Can Improve Model Robustness and Uncertaintycited by 373
  16. 2019Learning Loss for Active Learningcited by 335
  17. 2018Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problemcited by 323
  18. 2018Learning Confidence for Out-of-Distribution Detection in Neural Networkscited by 245
  19. 2015Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understandingcited by 218
  20. 2019Addressing Failure Prediction by Learning Model Confidencecited by 183
  21. 2020Efficient and Scalable Bayesian Neural Nets with Rank-1 Factorscited by 171
  22. 2018Deep Autoencoding Models for Unsupervised Anomaly Segmentation in Brain MR Imagescited by 146
  23. 2019Detecting the Unexpected via Image Resynthesiscited by 137
  24. 2019The Fishyscapes Benchmark: Measuring Blind Spots in Semantic Segmentationcited by 122
  25. 2020Synthesize then Compare: Detecting Failures and Anomalies for Semantic Segmentationcited by 96
  26. 2019Sampling-free Epistemic Uncertainty Estimation Using Approximated Variance Propagationcited by 74
  27. 2019Simultaneous Semantic Segmentation and Outlier Detection in Presence of Domain Shiftcited by 54
  28. 2019TRADI: Tracking deep neural network weight distributions for uncertainty estimationcited by 39
  29. 2019Detecting Out-of-Distribution Examples with In-distribution Examples and Gram Matricescited by 32
  30. 2015Binary Classifier Calibration using an Ensemble of Near Isotonic Regression Modelscited by 21
  31. 2020Detection and Retrieval of Out-of-Distribution Objects in Semantic Segmentationcited by 20
  32. 2018Failure Prediction for Autonomous Drivingcited by 14
  33. 2020PEP: Parameter Ensembling by Perturbationcited by 9
  34. 2021Learning Uncertainty For Safety-Oriented Semantic Segmentation In Autonomous Drivingcited by 8
  35. 2019I Bet You Are Wrong: Gambling Adversarial Networks for Structured Semantic Segmentationcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 10; 2023: 15; 2024: 11; 2025: 2; 2026: 1.

40 papers.

Sort:

By area:

  1. 2022VOS: Learning What You Don't Know by Virtual Outlier Synthesiscited by 300
  2. 2021Unsolved Problems in ML Safetycited by 291
  3. 2022RbA: Segmenting Unknown Regions Rejected by Allcited by 67
  4. 2023On Advantages of Mask-level Recognition for Outlier-aware Segmentationcited by 42
  5. 2023Maskomaly:Zero-Shot Mask Anomaly Segmentationcited by 34
  6. 2022MUAD: Multiple Uncertainties for Autonomous Driving, a benchmark for multiple uncertainty types and taskscited by 24
  7. 2024Open-World Semantic Segmentation Including Class Similaritycited by 22
  8. 2024PixOOD: Pixel-Level Out-of-Distribution Detectioncited by 20
  9. 2022Two Video Data Sets for Tracking and Retrieval of Out of Distribution Objectscited by 19
  10. 2022Latent Discriminant deterministic Uncertaintycited by 17
  11. 2024Manipulation Facing Threats: Evaluating Physical Vulnerabilities in End-to-End Vision Language Action Modelscited by 16
  12. 2022Far Away in the Deep Space: Dense Nearest-Neighbor-Based Out-of-Distribution Detectioncited by 15
28 more
  1. 2023UGainS: Uncertainty Guided Anomaly Instance Segmentationcited by 15
  2. 2024AnoVox: A Benchmark for Multimodal Anomaly Detection in Autonomous Drivingcited by 14
  3. 2022RODD: A Self-Supervised Approach for Robust Out-of-Distribution Detectioncited by 13
  4. 2023Panoptic Out-of-Distribution Segmentationcited by 13
  5. 2024Placing Objects in Context via Inpainting for Out-of-distribution Segmentationcited by 12
  6. 2023Pixel-wise Gradient Uncertainty for Convolutional Neural Networks applied to Out-of-Distribution Segmentationcited by 11
  7. 2023Hybrid Open-set Segmentation with Synthetic Negative Datacited by 8
  8. 2023Concurrent Misclassification and Out-of-Distribution Detection for Semantic Segmentation via Energy-Based Normalizing Flowcited by 8
  9. 2023ProbVLM: Probabilistic Adapter for Frozen Vision-Language Modelscited by 7
  10. 2023Discretization-Induced Dirichlet Posterior for Robust Uncertainty Quantification on Regressioncited by 7
  11. 2022Monitoring of Perception Systems: Deterministic, Probabilistic, and Learning-based Fault Detection and Identificationcited by 6
  12. 2024The BRAVO Semantic Segmentation Challenge Results in UNCV2024cited by 6
  13. 2023Anomaly-Aware Semantic Segmentation via Style-Aligned OoD Augmentationcited by 5
  14. 2023The Robust Semantic Segmentation UNCV2023 Challenge Resultscited by 5
  15. 2023Compensating for Sensing Failures via Delegation in Human-AI Hybrid Systemscited by 4
  16. 2024VL4AD: Vision-Language Models Improve Pixel-wise Anomaly Detectioncited by 4
  17. 2022Probing Contextual Diversity for Dense Out-of-Distribution Detectioncited by 3
  18. 2023Likelihood Annealing: Fast Calibrated Uncertainty for Regressioncited by 3
  19. 2024Optimizing Delegation in Collaborative Human-AI Hybrid Teamscited by 3
  20. 2024Multi-Scale Foreground-Background Confidence for Out-of-Distribution Segmentationcited by 3
  21. 2023Detection of Uncertainty in Exceedance of Threshold (DUET): An Adversarial Patch Localizercited by 2
  22. 2023Learning to Generate Training Datasets for Robust Semantic Segmentationcited by 2
  23. 2025OoDDINO:A Multi-level Framework for Anomaly Segmentation on Complex Road Scenescited by 2
  24. 2022Instance-Aware Observer Network for Out-of-Distribution Object Segmentationcited by 0
  25. 2024Critic Loss for Image Classificationcited by 0
  26. 2024Computable Model-Independent Bounds for Adversarial Quantum Machine Learningcited by 0
  27. 2025Language-Guided Open-World Anomaly Segmentationcited by 0
  28. 2026Combining Foundation Model Confidence and Monocular Depth for Training-Free Out-of-Distribution Segmentationcited by 0