mlsanityData to 7 Oct 2026

Detecting semantic anomalies

arXiv 1908.04388 ↗First posted 13 Aug 2019cs.CV cs.LGcited by 50

Not on the map. Why?

Abstract (arXiv)

We critically appraise the recent interest in out-of-distribution (OOD) detection and question the practical relevance of existing benchmarks. While the currently prevalent trend is to consider different datasets as OOD, we argue that out-distributions of practical interest are ones where the distinction is semantic in nature for a specified context, and that evaluative tasks should reflect this more closely. Assuming a context of object recognition, we recommend a set of benchmarks, motivated by practical applications. We make progress on these benchmarks by exploring a multi-task learning based approach, showing that auxiliary objectives for improved semantic awareness result in improved semantic anomaly detection, with accompanying generalization benefits.

Key facts. Cited by 50 papers in the map (data through 7 Oct 2026). First posted on arXiv 13 Aug 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 14; 2022: 9; 2023: 8; 2024: 8; 2025: 6; 2026: 5.

50 papers.

Sort:

By area:

  1. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  2. 2022A Unified Model for Multi-class Anomaly Detectioncited by 267
  3. 2022OpenOOD: Benchmarking Generalized Out-of-Distribution Detectioncited by 267
  4. 2023OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detectioncited by 178
  5. 2021A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challengescited by 154
  6. 2021Mean-Shifted Contrastive Loss for Anomaly Detectioncited by 87
  7. 2021Types of Out-of-Distribution Texts and How to Detect Themcited by 80
  8. 2021Mixture Outlier Exposure: Towards Out-of-Distribution Detection in Fine-grained Environmentscited by 65
  9. 2024A Closer Look at AUROC and AUPRC under Class Imbalancecited by 56
  10. 2022A Call to Reflect on Evaluation Practices for Failure Detection in Image Classificationcited by 51
  11. 2022Exposing Outlier Exposure: What Can Be Learned From Few, One, and Zero Outlier Imagescited by 35
  12. 2021On the Out-of-distribution Generalization of Probabilistic Image Modellingcited by 32
38 more
  1. 2021No True State-of-the-Art? OOD Detection Methods are Inconsistent across Datasetscited by 31
  2. 2021Transformaly -- Two (Feature Spaces) Are Better Than Onecited by 25
  3. 2024Out-of-distribution Detection in Medical Image Analysis: A surveycited by 22
  4. 2021CODEs: Chamfer Out-of-Distribution Examples against Overconfidence Issuecited by 14
  5. 2024Looking 3D: Anomaly Detection with 2D-3D Alignmentcited by 13
  6. 2023Fine-Tuning Deteriorates General Textual Out-of-Distribution Detection by Distorting Task-Agnostic Featurescited by 12
  7. 2021Transfer Learning Gaussian Anomaly Detection by Fine-tuning Representationscited by 10
  8. 2022Fine-grain Inference on Out-of-Distribution Data with Hierarchical Classificationcited by 10
  9. 2024Anomaly Detection Based on Isolation Mechanisms: A Surveycited by 10
  10. 2023No Free Lunch: The Hazards of Over-Expressive Representations in Anomaly Detectioncited by 7
  11. 2022READ: Aggregating Reconstruction Error into Out-of-distribution Detectioncited by 6
  12. 2024When and How Does In-Distribution Label Help Out-of-Distribution Detection?cited by 6
  13. 2021Data Invariants to Understand Unsupervised Out-of-Distribution Detectioncited by 5
  14. 2025GOOD: Training-Free Guided Diffusion Sampling for Out-of-Distribution Detectioncited by 5
  15. 2024Odd-One-Out: Anomaly Detection by Comparing with Neighborscited by 4
  16. 2021Multi-Class Anomaly Detectioncited by 3
  17. 2022TRUST-LAPSE: An Explainable and Actionable Mistrust Scoring Framework for Model Monitoringcited by 3
  18. 2022Beyond Mahalanobis-Based Scores for Textual OOD Detectioncited by 3
  19. 2025Safety Monitoring for Learning-Enabled Cyber-Physical Systems in Out-of-Distribution Scenarioscited by 3
  20. 2021OMASGAN: Out-of-Distribution Minimum Anomaly Score GAN for Sample Generation on the Boundarycited by 2
  21. 2023Understanding normalization in contrastive representation learning and out-of-distribution detectioncited by 2
  22. 2025Probability Density from Latent Diffusion Models for Out-of-Distribution Detectioncited by 2
  23. 2021Improving Novelty Detection using the Reconstructions of Nearest Neighbourscited by 1
  24. 2023SIO: Synthetic In-Distribution Data Benefits Out-of-Distribution Detectioncited by 1
  25. 2023Robust Novelty Detection through Style-Conscious Feature Rankingcited by 1
  26. 2024Embracing Unknown Step by Step: Towards Reliable Sparse Training in Real Worldcited by 1
  27. 2024Toward a Realistic Benchmark for Out-of-Distribution Detectioncited by 1
  28. 2025Efficient Odd-One-Out Anomaly Detectioncited by 1
  29. 2025BootOOD: Self-Supervised Out-of-Distribution Detection via Synthetic Sample Exposure under Neural Collapsecited by 1
  30. 2026ICONIC-444: A 3.1-Million-Image Dataset for OOD Detection Researchcited by 1
  31. 2026Axle Sensor Fusion for Online Continual Wheel Fault Detection in Wayside Railway Monitoringcited by 1
  32. 2022Bridging Machine Learning and Sciences: Opportunities and Challengescited by 0
  33. 2023CA2: Class-Agnostic Adaptive Feature Adaptation for One-class Classificationcited by 0
  34. 2023Environment-biased Feature Ranking for Novelty Detection Robustnesscited by 0
  35. 2025Real-Time Decorrelation-Based Anomaly Detection for Multivariate Time Seriescited by 0
  36. 2026Dual Feature Decoupling for Fine-Grained OOD Detectioncited by 0
  37. 2026Modality-Aware Out-of-Distribution Detection for Multi-Modal Action Recognitioncited by 0
  38. 2026Exploiting Local Flatness for Efficient Out-of-Distribution Detectioncited by 0