mlsanityData to 7 Oct 2026

Maskomaly:Zero-Shot Mask Anomaly Segmentation

arXiv 2305.16972 ↗First posted 26 May 2023cs.CVcited by 34

Not on the map. Why?

Abstract (arXiv)

We present a simple and practical framework for anomaly segmentation called Maskomaly. It builds upon mask-based standard semantic segmentation networks by adding a simple inference-time post-processing step which leverages the raw mask outputs of such networks. Maskomaly does not require additional training and only adds a small computational overhead to inference. Most importantly, it does not require anomalous data at training. We show top results for our method on SMIYC, RoadAnomaly, and StreetHazards. On the most central benchmark, SMIYC, Maskomaly outperforms all directly comparable approaches. Further, we introduce a novel metric that benefits the development of robust anomaly segmentation methods and demonstrate its informativeness on RoadAnomaly.

Key facts. Cited by 34 papers in the map (data through 7 Oct 2026). Builds on 41 of its 52 references that are in the map. First posted on arXiv 26 May 2023.

Builds on

41 of 52 references.

References · 41

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  5. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  6. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,923
  7. 2016Pyramid Scene Parsing Networkcited by 2,472
  8. 2017CARLA: An Open Urban Driving Simulatorcited by 2,431
  9. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  10. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,338
  11. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
  12. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
29 more
  1. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  2. 2021Per-Pixel Classification is Not All You Need for Semantic Segmentationcited by 1,148
  3. 2018Deep Anomaly Detection with Outlier Exposurecited by 939
  4. 2019Scaling Out-of-Distribution Detection for Real-World Settingscited by 465
  5. 2018Do Deep Generative Models Know What They Don't Know?cited by 443
  6. 2017Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samplescited by 389
  7. 2019Input complexity and out-of-distribution detection with likelihood-based generative modelscited by 186
  8. 2021SegmentMeIfYouCan: A Benchmark for Anomaly Segmentationcited by 150
  9. 2019Detecting the Unexpected via Image Resynthesiscited by 137
  10. 2018Improving Semantic Segmentation via Video Propagation and Label Relaxationcited by 134
  11. 2020Entropy Maximization and Meta Classification for Out-Of-Distribution Detection in Semantic Segmentationcited by 133
  12. 2019The Fishyscapes Benchmark: Measuring Blind Spots in Semantic Segmentationcited by 122
  13. 2021Pixel-wise Anomaly Detection in Complex Driving Scenescited by 109
  14. 2022Is Out-of-Distribution Detection Learnable?cited by 109
  15. 2020Synthesize then Compare: Detecting Failures and Anomalies for Semantic Segmentationcited by 96
  16. 2021Understanding Failures in Out-of-Distribution Detection with Deep Generative Modelscited by 89
  17. 2022GMMSeg: Gaussian Mixture based Generative Semantic Segmentation Modelscited by 87
  18. 2021Pixel-wise Energy-biased Abstention Learning for Anomaly Segmentation on Complex Urban Driving Scenescited by 83
  19. 2021Standardized Max Logits: A Simple yet Effective Approach for Identifying Unexpected Road Obstacles in Urban-Scene Segmentationcited by 77
  20. 2019Simultaneous Semantic Segmentation and Outlier Detection in Presence of Domain Shiftcited by 54
  21. 2021Deep Metric Learning for Open World Semantic Segmentationcited by 51
  22. 2022DenseHybrid: Hybrid Anomaly Detection for Dense Open-set Recognitioncited by 42
  23. 2021Triggering Failures: Out-Of-Distribution detection by learning from local adversarial attacks in Semantic Segmentationcited by 40
  24. 2019TRADI: Tracking deep neural network weight distributions for uncertainty estimationcited by 39
  25. 2020Dense open-set recognition with synthetic outliers generated by Real NVPcited by 29
  26. 2020Detection and Retrieval of Out-of-Distribution Objects in Semantic Segmentationcited by 20
  27. 2019Efficient Ladder-style DenseNets for Semantic Segmentation of Large Imagescited by 17
  28. 2020One Versus all for deep Neural Network Incertitude (OVNNI) quantificationcited by 17
  29. 2023Hybrid Open-set Segmentation with Synthetic Negative Datacited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 14; 2025: 11; 2026: 6.

34 papers.

Sort:

By area:

  1. 2024Outlier detection by ensembling uncertainty with negative objectnesscited by 34
  2. 2023Target before Shooting: Accurate Anomaly Detection and Localization under One Millisecond via Cascade Patch Retrievalcited by 22
  3. 2024Open-World Semantic Segmentation Including Class Similaritycited by 22
  4. 2023Mask2Anomaly: Mask Transformer for Universal Open-set Segmentationcited by 18
  5. 2024AnoVox: A Benchmark for Multimodal Anomaly Detection in Autonomous Drivingcited by 14
  6. 2025Out-of-Distribution Segmentation in Autonomous Driving: Problems and State of the Artcited by 13
  7. 2024A Likelihood Ratio-Based Approach to Segmenting Unknown Objectscited by 12
  8. 2023CoralVOS: Dataset and Benchmark for Coral Video Segmentationcited by 9
  9. 2024Diffusion for Out-of-Distribution Detection on Road Scenes and Beyondcited by 9
  10. 2025Prior2Former -- Evidential Modeling of Mask Transformers for Assumption-Free Open-World Panoptic Segmentationcited by 7
  11. 2024Finding Dino: A Plug-and-Play Framework for Zero-Shot Detection of Out-of-Distribution Objects Using Prototypescited by 5
  12. 2024MC-PanDA: Mask Confidence for Panoptic Domain Adaptationcited by 4
22 more
  1. 2024VL4AD: Vision-Language Models Improve Pixel-wise Anomaly Detectioncited by 4
  2. 2024UMAD: Unsupervised Mask-Level Anomaly Detection for Autonomous Drivingcited by 3
  3. 2024Segment-Level Road Obstacle Detection Using Visual Foundation Model Priors and Likelihood Ratioscited by 3
  4. 2024Multi-Scale Foreground-Background Confidence for Out-of-Distribution Segmentationcited by 3
  5. 2025Uncertainty-Aware Likelihood Ratio Estimation for Pixel-Wise Out-of-Distribution Detectioncited by 3
  6. 2024Open-World Panoptic Segmentationcited by 2
  7. 2025Out-of-Distribution Semantic Occupancy Predictioncited by 2
  8. 2025Road Obstacle Video Segmentationcited by 2
  9. 2024Random Walk on Pixel Manifolds for Anomaly Segmentation of Complex Driving Scenescited by 1
  10. 2025Anomalies by Synthesis: Anomaly Detection using Generative Diffusion Models for Off-Road Navigationcited by 1
  11. 2024Neural Network Meta Classifier: Improving the Reliability of Anomaly Segmentationcited by 0
  12. 2025Multi-modality Anomaly Segmentation on the Roadcited by 0
  13. 2025Panoramic Out-of-Distribution Segmentationcited by 0
  14. 2025Objectomaly: Objectness-Aware Refinement for OoD Segmentation with Structural Consistency and Boundary Precisioncited by 0
  15. 2025Training-Free Out-Of-Distribution Segmentation With Foundation Modelscited by 0
  16. 2025Language-Guided Open-World Anomaly Segmentationcited by 0
  17. 2026Vision-Language Feature Alignment for Road Anomaly Segmentationcited by 0
  18. 2026Road-Aware Anomaly Segmentation with Query-Guided Polygons and CLIP in Autonomous Drivingcited by 0
  19. 2026LARAD: Layout-Aware Road Anomaly Detection via Spatial-Logic Reasoningcited by 0
  20. 2026Combining Foundation Model Confidence and Monocular Depth for Training-Free Out-of-Distribution Segmentationcited by 0
  21. 2026SAFe: Segment-guided Aggregation of Feature Densities for Anomaly-aware Segmentationcited by 0
  22. 2026MC-PanDA++: Simpler, Stronger, and More Robust Domain-Adaptive Panoptic Segmentationcited by 0