mlsanityData to 7 Oct 2026

Rethinking Assumptions in Deep Anomaly Detection

arXiv 2006.00339 ↗First posted 30 May 2020cs.LG stat.MLcited by 45

Not on the map. Why?

Abstract (arXiv)

Though anomaly detection (AD) can be viewed as a classification problem (nominal vs. anomalous) it is usually treated in an unsupervised manner since one typically does not have access to, or it is infeasible to utilize, a dataset that sufficiently characterizes what it means to be "anomalous." In this paper we present results demonstrating that this intuition surprisingly seems not to extend to deep AD on images. For a recent AD benchmark on ImageNet, classifiers trained to discern between normal samples and just a few (64) random natural images are able to outperform the current state of the art in deep AD. Experimentally we discover that the multiscale structure of image data makes example anomalies exceptionally informative.

Key facts. Cited by 45 papers in the map (data through 7 Oct 2026). First posted on arXiv 30 May 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 9; 2022: 14; 2023: 9; 2024: 7; 2025: 6.

45 papers.

Sort:

  1. 2021Mean-Shifted Contrastive Loss for Anomaly Detectioncited by 87
  2. 2022Explicit Boundary Guided Semi-Push-Pull Contrastive Learning for Supervised Anomaly Detectioncited by 72
  3. 2023GADBench: Revisiting and Benchmarking Supervised Graph Anomaly Detectioncited by 57
  4. 2022TFAD: A Decomposition Time Series Anomaly Detection Architecture with Time-Frequency Analysiscited by 48
  5. 2021Neural Contextual Anomaly Detection for Time Seriescited by 42
  6. 2022Exposing Outlier Exposure: What Can Be Learned From Few, One, and Zero Outlier Imagescited by 35
  7. 2024Large Language Model Guided Knowledge Distillation for Time Series Anomaly Detectioncited by 26
  8. 2022Data Augmentation is a Hyperparameter: Cherry-picked Self-Supervision for Unsupervised Anomaly Detection is Creating the Illusion of Successcited by 11
  9. 2021Transfer Learning Gaussian Anomaly Detection by Fine-tuning Representationscited by 10
  10. 2022Towards Accurate Open-Set Recognition via Background-Class Regularizationcited by 10
  11. 2023LARA: A Light and Anti-overfitting Retraining Approach for Unsupervised Time Series Anomaly Detectioncited by 9
  12. 2024AI-based Anomaly Detection for Clinical-Grade Histopathological Diagnosticscited by 8
33 more
  1. 2021Understanding the Effect of Bias in Deep Anomaly Detectioncited by 7
  2. 2025INP-Former++: Advancing Universal Anomaly Detection via Intrinsic Normal Prototypes and Residual Learningcited by 7
  3. 2022Anomaly Detection in Echocardiograms with Dynamic Variational Trajectory Modelscited by 5
  4. 2023One-class Damage Detector Using Deeper Fully-Convolutional Data Descriptions for Civil Applicationcited by 5
  5. 2024Towards Cross-domain Few-shot Graph Anomaly Detectioncited by 5
  6. 2022Data refinement for fully unsupervised visual inspection using pre-trained networkscited by 4
  7. 2021Data augmentation and pre-trained networks for extremely low data regimes unsupervised visual inspectioncited by 3
  8. 2021Deep Random Projection Outlyingness for Unsupervised Anomaly Detectioncited by 3
  9. 2021Anomaly Detection in IR Images of PV Modules using Supervised Contrastive Learningcited by 3
  10. 2022No Shifted Augmentations (NSA): compact distributions for robust self-supervised Anomaly Detectioncited by 3
  11. 2022Semi-supervised anomaly detection algorithm based on KL divergence (SAD-KL)cited by 2
  12. 2023Set Learning for Accurate and Calibrated Modelscited by 2
  13. 2023Restricted Generative Projection for One-Class Classification and Anomaly Detectioncited by 2
  14. 2024Semi-supervised Anomaly Detection via Adaptive Reinforcement Learning-Enabled Method with Causal Inference for Sensor Signalscited by 2
  15. 2025Semi-supervised Anomaly Detection with Extremely Limited Labels in Dynamic Graphscited by 2
  16. 2025ResAD++: Towards Class Agnostic Anomaly Detection via Residual Feature Learningcited by 2
  17. 2021Anomalous Sound Detection Using a Binary Classification Model and Class Centroidscited by 1
  18. 2021Out-of-Distribution Detection Using Outlier Detection Methodscited by 1
  19. 2023Wooden Sleeper Deterioration Detection for Rural Railway Prognostics Using Unsupervised Deeper FCDDscited by 1
  20. 2023Few-shot 1/a Anomalies Feedback : Damage Vision Mining Opportunity and Embedding Feature Imbalancecited by 1
  21. 2022Improving State-of-the-Art in One-Class Classification by Leveraging Unlabeled Datacited by 0
  22. 2022[Reproducibility Report] Explainable Deep One-Class Classificationcited by 0
  23. 2022Deep Anomaly Detection and Search via Reinforcement Learningcited by 0
  24. 2022Collaborative Anomaly Detectioncited by 0
  25. 2022InForecaster: Forecasting Influenza Hemagglutinin Mutations Through the Lens of Anomaly Detectioncited by 0
  26. 2023Adapting the Hypersphere Loss Function from Anomaly Detection to Anomaly Segmentationcited by 0
  27. 2023Disaster Anomaly Detector via Deeper FCDDs for Explainable Initial Responsescited by 0
  28. 2024Cell Culture Assistive Application for Precipitation Image Diagnosiscited by 0
  29. 2024MeLIAD: Interpretable Few-Shot Anomaly Detection with Metric Learning and Entropy-based Scoringcited by 0
  30. 2024GraphSubDetector: Time Series Subsequence Anomaly Detection via Density-Aware Adaptive Graph Neural Networkcited by 0
  31. 2025Beyond Academic Benchmarks: Critical Analysis and Best Practices for Visual Industrial Anomaly Detectioncited by 0
  32. 2025CAPMix: Robust KPI Anomaly Detection for AIOps in Noisy and Dynamic Environmentscited by 0
  33. 2025Enhancing Time-Series Anomaly Detection by Integrating Spectral-Residual Bottom-Up Attention with Reservoir Computingcited by 0