mlsanityData to 7 Oct 2026

Anomaly Detection under Distribution Shift

arXiv 2303.13845 ↗First posted 24 Mar 2023cs.CVcited by 35

Not on the map. Why?

Abstract (arXiv)

Anomaly detection (AD) is a crucial machine learning task that aims to learn patterns from a set of normal training samples to identify abnormal samples in test data. Most existing AD studies assume that the training and test data are drawn from the same data distribution, but the test data can have large distribution shifts arising in many real-world applications due to different natural variations such as new lighting conditions, object poses, or background appearances, rendering existing AD methods ineffective in such cases. In this paper, we consider the problem of anomaly detection under distribution shift and establish performance benchmarks on four widely-used AD and out-of-distribution (OOD) generalization datasets. We demonstrate that simple adaptation of state-of-the-art OOD generalization methods to AD settings fails to work effectively due to the lack of labeled anomaly data. We further introduce a novel robust AD approach to diverse distribution shifts by minimizing the distribution gap between in-distribution and OOD normal samples in both the training and inference stages in an unsupervised way. Our extensive empirical results on the four datasets show that our approach substantially outperforms state-of-the-art AD methods and OOD generalization methods on data with various distribution shifts, while maintaining the detection accuracy on in-distribution data. Code and data are available at https://github.com/mala-lab/ADShift.

Key facts. Cited by 35 papers in the map (data through 7 Oct 2026). Builds on 63 of its 93 references that are in the map. First posted on arXiv 24 Mar 2023.

Builds on

63 of 93 references.

References · 63

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  4. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  5. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  6. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  7. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,366
  8. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  9. 2017Deeper, Broader and Artier Domain Generalizationcited by 983
  10. 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 897
  11. 2013Domain Generalization via Invariant Feature Representationcited by 622
  12. 2021Domain Generalization with MixStylecited by 563
38 more
  1. 2019Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detectioncited by 560
  2. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 529
  3. 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 451
  4. 2019Domain Generalization by Solving Jigsaw Puzzlescited by 449
  5. 2020Self-Challenging Improves Cross-Domain Generalizationcited by 426
  6. 2022Anomaly Detection via Reverse Distillation from One-Class Embeddingcited by 419
  7. 2018GANomaly: Semi-Supervised Anomaly Detection via Adversarial Trainingcited by 409
  8. 2020Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Datacited by 408
  9. 2019Domain Generalization via Model-Agnostic Learning of Semantic Featurescited by 405
  10. 2019Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddingscited by 386
  11. 2017Certifying Some Distributional Robustness with Principled Adversarial Trainingcited by 333
  12. 2020Learning to Learn Single Domain Generalizationcited by 295
  13. 2020Multiresolution Knowledge Distillation for Anomaly Detectioncited by 285
  14. 2021FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Spacecited by 284
  15. 2020Learning Memory-guided Normality for Anomaly Detectioncited by 278
  16. 2015Domain Generalization for Object Recognition with Multi-task Autoencoderscited by 253
  17. 2020Domain Generalization using Causal Matchingcited by 224
  18. 2020Patch SVDD: Patch-level SVDD for Anomaly Detection and Segmentationcited by 212
  19. 2019OCGAN: One-class Novelty Detection Using GANs with Constrained Latent Representationscited by 199
  20. 2021Student-Teacher Feature Pyramid Matching for Anomaly Detectioncited by 145
  21. 2020Efficient Domain Generalization via Common-Specific Low-Rank Decompositioncited by 134
  22. 2020Learning to Balance Specificity and Invariance for In and Out of Domain Generalizationcited by 128
  23. 2020Domain Generalization for Medical Imaging Classification with Linear-Dependency Regularizationcited by 122
  24. 2022Exact Feature Distribution Matching for Arbitrary Style Transfer and Domain Generalizationcited by 122
  25. 2020DROCC: Deep Robust One-Class Classificationcited by 121
  26. 2021Causality-inspired Single-source Domain Generalization for Medical Image Segmentationcited by 118
  27. 2020Old is Gold: Redefining the Adversarially Learned One-Class Classifier Training Paradigmcited by 115
  28. 2019DIVA: Domain Invariant Variational Autoencoderscited by 114
  29. 2020Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identificationcited by 110
  30. 2020Learning from Extrinsic and Intrinsic Supervisions for Domain Generalizationcited by 108
  31. 2022Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detectioncited by 104
  32. 2020Learning to Learn with Variational Information Bottleneck for Domain Generalizationcited by 102
  33. 2020Cross-domain Face Presentation Attack Detection via Multi-domain Disentangled Representation Learningcited by 93
  34. 2021Divide-and-Assemble: Learning Block-wise Memory for Unsupervised Anomaly Detectioncited by 83
  35. 2021Learning Normal Dynamics in Videos with Meta Prototype Networkcited by 71
  36. 2019Domain Generalization via Multidomain Discriminant Analysiscited by 69
  37. 2021Deep One-Class Classification via Interpolated Gaussian Descriptorcited by 67
  38. 2020Few-shot Scene-adaptive Anomaly Detectioncited by 62

50 most cited of 63 All 63 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 12; 2025: 12; 2026: 8.

35 papers.

Sort:

By area:

  1. 2023AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detectioncited by 270
  2. 2024Toward Generalist Anomaly Detection via In-context Residual Learning with Few-shot Sample Promptscited by 88
  3. 2025Towards Zero-Shot Anomaly Detection and Reasoning with Multimodal Large Language Modelscited by 54
  4. 2024ARC: A Generalist Graph Anomaly Detector with In-Context Learningcited by 46
  5. 2024GeneralAD: Anomaly Detection Across Domains by Attending to Distorted Featurescited by 29
  6. 2024PointAD: Comprehending 3D Anomalies from Points and Pixels for Zero-shot 3D Anomaly Detectioncited by 29
  7. 2023Anomaly Heterogeneity Learning for Open-set Supervised Anomaly Detectioncited by 25
  8. 2024Fine-grained Abnormality Prompt Learning for Zero-shot Anomaly Detectioncited by 22
  9. 2024Learning Feature Inversion for Multi-class Anomaly Detection under General-purpose COCO-AD Benchmarkcited by 15
  10. 2024Salvaging the Overlooked: Leveraging Class-Aware Contrastive Learning for Multi-Class Anomaly Detectioncited by 15
  11. 2024FOOGD: Federated Collaboration for Both Out-of-distribution Generalization and Detectioncited by 14
  12. 2024COFT-AD: COntrastive Fine-Tuning for Few-Shot Anomaly Detectioncited by 13
23 more
  1. 2025Normal-Abnormal Guided Generalist Anomaly Detectioncited by 10
  2. 2025One-to-Normal: Anomaly Personalization for Few-shot Anomaly Detectioncited by 7
  3. 2025Subject Information Extraction for Novelty Detection with Domain Shiftscited by 6
  4. 2024ROADS: Robust Prompt-driven Multi-Class Anomaly Detection under Domain Shiftcited by 5
  5. 2025Robust Distribution Alignment for Industrial Anomaly Detection under Distribution Shiftcited by 5
  6. 2026Dual Distillation for Few-Shot Anomaly Detectioncited by 3
  7. 2025FedDAG: Federated Domain Adversarial Generation Towards Generalizable Medical Image Analysiscited by 2
  8. 2025MCL-AD: Multimodal Collaboration Learning for Zero-Shot 3D Anomaly Detectioncited by 2
  9. 2025ResAD++: Towards Class Agnostic Anomaly Detection via Residual Feature Learningcited by 2
  10. 2023Multilevel Saliency-Guided Self-Supervised Learning for Image Anomaly Detectioncited by 1
  11. 2025PointAD+: Learning Hierarchical Representations for Zero-shot 3D Anomaly Detectioncited by 1
  12. 2026FB-CLIP: Fine-Grained Zero-Shot Anomaly Detection with Foreground-Background Disentanglementcited by 1
  13. 2026CL-Anomaly: Layer-Adaptive Mixture-of-Experts with Multimodal Large Language Model for Continual Learning in Anomaly Detectioncited by 1
  14. 2024MAPL: Memory Augmentation and Pseudo-Labeling for Semi-Supervised Anomaly Detectioncited by 0
  15. 2024On The Relationship between Visual Anomaly-free and Anomalous Representationscited by 0
  16. 2025When Unsupervised Domain Adaptation meets One-class Anomaly Detection: Addressing the Two-fold Unsupervised Curse by Leveraging Anomaly Scarcitycited by 0
  17. 2025Language-Assisted Feature Transformation for Anomaly Detectioncited by 0
  18. 2025Open-Set Domain Adaptation Under Background Distribution Shift: Challenges and A Provably Efficient Solutioncited by 0
  19. 2026Out of Context: Reliability in Multimodal Anomaly Detection Requires Contextual Inferencecited by 0
  20. 2026Align3D-AD: Cross-Modal Feature Alignment and Dual-Prompt Learning for Zero-shot 3D Anomaly Detectioncited by 0
  21. 2026Beyond Normal References: Discriminative Few-Shot Anomaly Detectioncited by 0
  22. 2026Value-order Decomposition for Generalist Anomaly Detectioncited by 0
  23. 2026ShiftSplit-AD: Separating Domain Shift from Defects in Foundation-Feature Visual Anomaly Detectioncited by 0