mlsanityData to 7 Oct 2026

On Advantages of Mask-level Recognition for Outlier-aware Segmentation

arXiv 2301.03407 ↗First posted 9 Jan 2023cs.CVcited by 42

Not on the map. Why?

Abstract (arXiv)

Most dense recognition approaches bring a separate decision in each particular pixel. These approaches deliver competitive performance in usual closed-set setups. However, important applications in the wild typically require strong performance in presence of outliers. We show that this demanding setup greatly benefit from mask-level predictions, even in the case of non-finetuned baseline models. Moreover, we propose an alternative formulation of dense recognition uncertainty that effectively reduces false positive responses at semantic borders. The proposed formulation produces a further improvement over a very strong baseline and sets the new state of the art in outlier-aware semantic segmentation with and without training on negative data. Our contributions also lead to performance improvement in a recent panoptic setup. In-depth experiments confirm that our approach succeeds due to implicit aggregation of pixel-level cues into mask-level predictions.

Key facts. Cited by 42 papers in the map (data through 7 Oct 2026). Builds on 53 of its 65 references that are in the map. First posted on arXiv 9 Jan 2023.

Builds on

53 of 65 references.

References · 53

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  3. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  4. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  5. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  6. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  7. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,338
  8. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  9. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  10. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  11. 2021Per-Pixel Classification is Not All You Need for Semantic Segmentationcited by 1,148
  12. 2016Semantic Understanding of Scenes through the ADE20K Datasetcited by 1,063
38 more
  1. 2016HyperNetworkscited by 1,003
  2. 2018Deep Anomaly Detection with Outlier Exposurecited by 939
  3. 2018Predictive Uncertainty Estimation via Prior Networkscited by 555
  4. 2015Towards Open Set Deep Networkscited by 533
  5. 2019Scaling Out-of-Distribution Detection for Real-World Settingscited by 465
  6. 2018Do Deep Generative Models Know What They Don't Know?cited by 443
  7. 2019PointRend: Image Segmentation as Renderingcited by 439
  8. 2020A Unifying Review of Deep and Shallow Anomaly Detectioncited by 423
  9. 2017Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samplescited by 389
  10. 2019Panoptic-DeepLabcited by 362
  11. 2021Open-Set Recognition: a Good Closed-Set Classifier is All You Need?cited by 351
  12. 2022Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentationcited by 341
  13. 2020Why Normalizing Flows Fail to Detect Out-of-Distribution Datacited by 220
  14. 2019Input complexity and out-of-distribution detection with likelihood-based generative modelscited by 186
  15. 2014Simultaneous Detection and Segmentationcited by 158
  16. 2021Adversarial Reciprocal Points Learning for Open Set Recognitioncited by 153
  17. 2015Stereo Matching by Training a Convolutional Neural Network to Compare Image Patchescited by 151
  18. 2021SegmentMeIfYouCan: A Benchmark for Anomaly Segmentationcited by 150
  19. 2018Evaluating Bayesian Deep Learning Methods for Semantic Segmentationcited by 143
  20. 2019Detecting the Unexpected via Image Resynthesiscited by 137
  21. 2020Entropy Maximization and Meta Classification for Out-Of-Distribution Detection in Semantic Segmentationcited by 133
  22. 2019The Fishyscapes Benchmark: Measuring Blind Spots in Semantic Segmentationcited by 122
  23. 2020Hybrid Models for Open Set Recognitioncited by 109
  24. 2021Pixel-wise Anomaly Detection in Complex Driving Scenescited by 109
  25. 2020Synthesize then Compare: Detecting Failures and Anomalies for Semantic Segmentationcited by 96
  26. 2022GMMSeg: Gaussian Mixture based Generative Semantic Segmentation Modelscited by 87
  27. 2021Pixel-wise Energy-biased Abstention Learning for Anomaly Segmentation on Complex Urban Driving Scenescited by 83
  28. 2017In-Place Activated BatchNorm for Memory-Optimized Training of DNNscited by 81
  29. 2021Standardized Max Logits: A Simple yet Effective Approach for Identifying Unexpected Road Obstacles in Urban-Scene Segmentationcited by 77
  30. 2016Learning to Refine Object Segmentscited by 67
  31. 2018Prediction Error Meta Classification in Semantic Segmentation: Detection via Aggregated Dispersion Measures of Softmax Probabilitiescited by 54
  32. 2019Simultaneous Semantic Segmentation and Outlier Detection in Presence of Domain Shiftcited by 54
  33. 2021Deep Metric Learning for Open World Semantic Segmentationcited by 51
  34. 2022DenseHybrid: Hybrid Anomaly Detection for Dense Open-set Recognitioncited by 42
  35. 2014Convolutional Feature Masking for Joint Object and Stuff Segmentationcited by 41
  36. 2021Triggering Failures: Out-Of-Distribution detection by learning from local adversarial attacks in Semantic Segmentationcited by 40
  37. 2021Exemplar-Based Open-Set Panoptic Segmentation Networkcited by 37
  38. 2020Dense open-set recognition with synthetic outliers generated by Real NVPcited by 29

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 5; 2024: 18; 2025: 13; 2026: 6.

42 papers.

Sort:

By area:

  1. 2024Outlier detection by ensembling uncertainty with negative objectnesscited by 34
  2. 2024PixOOD: Pixel-Level Out-of-Distribution Detectioncited by 20
  3. 2023CSL: Class-Agnostic Structure-Constrained Learning for Segmentation Including the Unseencited by 15
  4. 2024AnoVox: A Benchmark for Multimodal Anomaly Detection in Autonomous Drivingcited by 14
  5. 2025Out-of-Distribution Segmentation in Autonomous Driving: Problems and State of the Artcited by 13
  6. 2024A Likelihood Ratio-Based Approach to Segmenting Unknown Objectscited by 12
  7. 2023Pixel-wise Gradient Uncertainty for Convolutional Neural Networks applied to Out-of-Distribution Segmentationcited by 11
  8. 2023Have We Ever Encountered This Before? Retrieving Out-of-Distribution Road Obstacles from Driving Scenescited by 9
  9. 2024Diffusion for Out-of-Distribution Detection on Road Scenes and Beyondcited by 9
  10. 2024OoDIS: Anomaly Instance Segmentation and Detection Benchmarkcited by 8
  11. 2023Exploring the Potential of World Models for Anomaly Detection in Autonomous Drivingcited by 7
  12. 2025Prior2Former -- Evidential Modeling of Mask Transformers for Assumption-Free Open-World Panoptic Segmentationcited by 7
30 more
  1. 2023Anomaly-Aware Semantic Segmentation via Style-Aligned OoD Augmentationcited by 5
  2. 2024Finding Dino: A Plug-and-Play Framework for Zero-Shot Detection of Out-of-Distribution Objects Using Prototypescited by 5
  3. 2024Generalize or Detect? Towards Robust Semantic Segmentation Under Multiple Distribution Shiftscited by 5
  4. 2025Segmenting Objectiveness and Task-awareness Unknown Region for Autonomous Drivingcited by 5
  5. 2024MC-PanDA: Mask Confidence for Panoptic Domain Adaptationcited by 4
  6. 2024VL4AD: Vision-Language Models Improve Pixel-wise Anomaly Detectioncited by 4
  7. 2024Segment-Level Road Obstacle Detection Using Visual Foundation Model Priors and Likelihood Ratioscited by 3
  8. 2024Multi-Scale Foreground-Background Confidence for Out-of-Distribution Segmentationcited by 3
  9. 2025Uncertainty-Aware Likelihood Ratio Estimation for Pixel-Wise Out-of-Distribution Detectioncited by 3
  10. 2024Uncertainty estimates for semantic segmentation: providing enhanced reliability for automated motor claims handlingcited by 2
  11. 2024TESGNN: Temporal Equivariant Scene Graph Neural Networks for Efficient and Robust Multi-View 3D Scene Understandingcited by 2
  12. 2024FlowCLAS: Enhancing Normalizing Flow Via Contrastive Learning For Anomaly Segmentationcited by 2
  13. 2024Volumetric Mapping with Panoptic Refinement via Kernel Density Estimation for Mobile Robotscited by 2
  14. 2024Open-World Panoptic Segmentationcited by 2
  15. 2025Benchmarking Vision Foundation Models for Input Monitoring in Autonomous Drivingcited by 2
  16. 2025A Dataset for Semantic Segmentation in the Presence of Unknownscited by 2
  17. 2025Out-of-Distribution Semantic Occupancy Predictioncited by 2
  18. 2025Road Obstacle Video Segmentationcited by 2
  19. 2024Random Walk on Pixel Manifolds for Anomaly Segmentation of Complex Driving Scenescited by 1
  20. 2025From Pixel to Mask: A Survey of Out-of-Distribution Segmentationcited by 1
  21. 2025Multi-modality Anomaly Segmentation on the Roadcited by 0
  22. 2025Panoramic Out-of-Distribution Segmentationcited by 0
  23. 2025A Machine Learning Perspective on Automated Driving Corner Casescited by 0
  24. 2025Language-Guided Open-World Anomaly Segmentationcited by 0
  25. 2026ProOOD: Prototype-Guided Out-of-Distribution 3D Occupancy Predictioncited by 0
  26. 2026Hyp2Former: Hierarchy-Aware Hyperbolic Embeddings for Open-Set Panoptic Segmentationcited by 0
  27. 2026LARAD: Layout-Aware Road Anomaly Detection via Spatial-Logic Reasoningcited by 0
  28. 2026Combining Foundation Model Confidence and Monocular Depth for Training-Free Out-of-Distribution Segmentationcited by 0
  29. 2026SAFe: Segment-guided Aggregation of Feature Densities for Anomaly-aware Segmentationcited by 0
  30. 2026MC-PanDA++: Simpler, Stronger, and More Robust Domain-Adaptive Panoptic Segmentationcited by 0