mlsanityData to 7 Oct 2026

Latent Outlier Exposure for Anomaly Detection with Contaminated Data

arXiv 2202.08088 ↗First posted 16 Feb 2022cs.LG cs.AIcited by 48

Not on the map. Why?

Abstract (arXiv)

Anomaly detection aims at identifying data points that show systematic deviations from the majority of data in an unlabeled dataset. A common assumption is that clean training data (free of anomalies) is available, which is often violated in practice. We propose a strategy for training an anomaly detector in the presence of unlabeled anomalies that is compatible with a broad class of models. The idea is to jointly infer binary labels to each datum (normal vs. anomalous) while updating the model parameters. Inspired by outlier exposure (Hendrycks et al., 2018) that considers synthetically created, labeled anomalies, we thereby use a combination of two losses that share parameters: one for the normal and one for the anomalous data. We then iteratively proceed with block coordinate updates on the parameters and the most likely (latent) labels. Our experiments with several backbone models on three image datasets, 30 tabular data sets, and a video anomaly detection benchmark showed consistent and significant improvements over the baselines.

Key facts. Cited by 48 papers in the map (data through 7 Oct 2026). Builds on 22 of its 43 references that are in the map. First posted on arXiv 16 Feb 2022.

Builds on

22 of 43 references.

References · 22

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2018Deep Anomaly Detection with Outlier Exposurecited by 939
  3. 2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 591
  4. 2017Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoverycited by 566
  5. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 529
  6. 2019Using Self-Supervised Learning Can Improve Model Robustness and Uncertaintycited by 511
  7. 2018Do Deep Generative Models Know What They Don't Know?cited by 443
  8. 2020A Unifying Review of Deep and Shallow Anomaly Detectioncited by 423
  9. 2019Deep Semi-Supervised Anomaly Detectioncited by 290
  10. 2018Deep Anomaly Detection Using Geometric Transformationscited by 269
  11. 2020Classification-Based Anomaly Detection for General Datacited by 210
  12. 2020PANDA: Adapting Pretrained Features for Anomaly Detection and Segmentationcited by 175
10 more
  1. 2021MIST: Multiple Instance Self-Training Framework for Video Anomaly Detectioncited by 137
  2. 2020Learning and Evaluating Representations for Deep One-class Classificationcited by 133
  3. 2021Neural Transformation Learning for Deep Anomaly Detection Beyond Imagescited by 98
  4. 2018Unsupervised Detection of Lesions in Brain MRI using constrained adversarial auto-encoderscited by 83
  5. 2020Self-trained Deep Ordinal Regression for End-to-End Video Anomaly Detectioncited by 83
  6. 2017Unmasking the abnormal events in videocited by 48
  7. 2019Robust Anomaly Detection in Images using Adversarial Autoencoderscited by 38
  8. 2016A Discriminative Framework for Anomaly Detection in Large Videoscited by 25
  9. 2022Detecting Anomalies within Time Series using Local Neural Transformationscited by 12
  10. 2021Unsupervised Outlier Detection using Memory and Contrastive Learningcited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 6; 2023: 15; 2024: 15; 2025: 5; 2026: 7.

48 papers.

Sort:

By area:

  1. 2022ADBench: Anomaly Detection Benchmarkcited by 230
  2. 2023Deep Industrial Image Anomaly Detection: A Surveycited by 147
  3. 2023IM-IAD: Industrial Image Anomaly Detection Benchmark in Manufacturingcited by 64
  4. 2024SoftPatch: Unsupervised Anomaly Detection with Noisy Datacited by 55
  5. 2022Calibrated One-class Classification for Unsupervised Time Series Anomaly Detectioncited by 39
  6. 2023Fascinating Supervisory Signals and Where to Find Them: Deep Anomaly Detection with Scale Learningcited by 25
  7. 2022Detecting Multivariate Time Series Anomalies with Zero Known Labelcited by 21
  8. 2023Label-Free Multivariate Time Series Anomaly Detectioncited by 14
  9. 2024CLIPScope: Enhancing Zero-Shot OOD Detection with Bayesian Scoringcited by 13
  10. 2024Anomaly Detection of Tabular Data Using LLMscited by 12
  11. 2023Deep Anomaly Detection under Labeling Budget Constraintscited by 9
  12. 2024Learning Multi-view Anomaly Detection with Efficient Adaptive Selectioncited by 9
36 more
  1. 2023Anomaly Detection with Variance Stabilized Density Estimationcited by 8
  2. 2023Model Selection of Anomaly Detectors in the Absence of Labeled Validation Datacited by 8
  3. 2024FUN-AD: Fully Unsupervised Learning for Anomaly Detection with Noisy Training Datacited by 8
  4. 2024Toward Multi-class Anomaly Detection: Exploring Class-aware Unified Model against Inter-class Interferencecited by 7
  5. 2022Hierarchical Semi-Supervised Contrastive Learning for Contamination-Resistant Anomaly Detectioncited by 5
  6. 2023Robust online active learningcited by 5
  7. 2023TabADM: Unsupervised Tabular Anomaly Detection with Diffusion Modelscited by 5
  8. 2023Unilaterally Aggregated Contrastive Learning with Hierarchical Augmentation for Anomaly Detectioncited by 5
  9. 2024Hierarchical Visual Categories Modeling: A Joint Representation Learning and Density Estimation Framework for Out-of-Distribution Detectioncited by 4
  10. 2024Adaptive Deviation Learning for Visual Anomaly Detection with Data Contaminationcited by 4
  11. 2025RoCA: Robust Contrastive One-class Time Series Anomaly Detection with Contaminated Datacited by 4
  12. 2022Unsupervised Anomaly Detection for Auditing Data and Impact of Categorical Encodingscited by 3
  13. 2024EntropyStop: Unsupervised Deep Outlier Detection with Loss Entropycited by 3
  14. 2025An Evidence-Based Post-Hoc Adjustment Framework for Anomaly Detection Under Data Contaminationcited by 3
  15. 2026ICLAD: In-Context Learning for Unified Tabular Anomaly Detection Across Supervision Regimescited by 3
  16. 2022Identification of Rare Cortical Folding Patterns using Unsupervised Deep Learningcited by 2
  17. 2023OmniForce: On Human-Centered, Large Model Empowered and Cloud-Edge Collaborative AutoML Systemcited by 2
  18. 2023Anomaly detection with semi-supervised classification based on risk estimatorscited by 2
  19. 2024Uncertainty-aware Evaluation of Auxiliary Anomalies with the Expected Anomaly Posteriorcited by 2
  20. 2024Deep Positive-Unlabeled Anomaly Detection for Contaminated Unlabeled Datacited by 2
  21. 2025STAGE: Segmentation-oriented Industrial Anomaly Synthesis via Graded Diffusion with Explicit Mask Alignmentcited by 2
  22. 2023Zero-Shot Anomaly Detection via Batch Normalizationcited by 1
  23. 2024GradStop: Exploring Training Dynamics in Unsupervised Outlier Detection through Gradientcited by 1
  24. 2023A Generic Machine Learning Framework for Fully-Unsupervised Anomaly Detection with Contaminated Datacited by 0
  25. 2023Be Bayesian by Attachments to Catch More Uncertaintycited by 0
  26. 2024Two Is Better Than One: Aligned Representation Pairs for Anomaly Detectioncited by 0
  27. 2024Impact of Inaccurate Contamination Ratio on Robust Unsupervised Anomaly Detectioncited by 0
  28. 2024Out-of-Distribution Detection with Overlap Indexcited by 0
  29. 2025Beyond Academic Benchmarks: Critical Analysis and Best Practices for Visual Industrial Anomaly Detectioncited by 0
  30. 2025Anomaly Detection with Adaptive and Aggressive Rejection for Contaminated Training Datacited by 0
  31. 2026Multi-Cue Anomaly Detection and Localization under Data Contaminationcited by 0
  32. 2026Unsupervised Anomaly Detection of Information Operations Users via Behavioral and Language Patternscited by 0
  33. 2026Deep Convolutional Large-Margin ℓp-SVDD for Visual Anomaly Detectioncited by 0
  34. 2026Robust Unsupervised Network Intrusion Detection via Federated Learning with Selective Aggregation under Anomalous Sample Contaminationcited by 0
  35. 2026What Memory Composition Does Not Tell Us About Anomaly Detectioncited by 0
  36. 2026Multi-Modal Anomaly Detection: A Surveycited by 0