mlsanityData to 7 Oct 2026

A Hierarchical Transformation-Discriminating Generative Model for Few Shot Anomaly Detection

arXiv 2104.14535 ↗First posted 29 Apr 2021cs.CV cs.LGcited by 60

Not on the map. Why?

Abstract (arXiv)

Anomaly detection, the task of identifying unusual samples in data, often relies on a large set of training samples. In this work, we consider the setting of few-shot anomaly detection in images, where only a few images are given at training. We devise a hierarchical generative model that captures the multi-scale patch distribution of each training image. We further enhance the representation of our model by using image transformations and optimize scale-specific patch-discriminators to distinguish between real and fake patches of the image, as well as between different transformations applied to those patches. The anomaly score is obtained by aggregating the patch-based votes of the correct transformation across scales and image regions. We demonstrate the superiority of our method on both the one-shot and few-shot settings, on the datasets of Paris, CIFAR10, MNIST and FashionMNIST as well as in the setting of defect detection on MVTec. In all cases, our method outperforms the recent baseline methods.

Key facts. Cited by 60 papers in the map (data through 7 Oct 2026). Builds on 27 of its 45 references that are in the map. First posted on arXiv 29 Apr 2021.

Builds on

27 of 45 references.

References · 27

  1. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  2. 2016Improved Techniques for Training GANscited by 2,938
  3. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  4. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
  5. 2017Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networkscited by 707
  6. 2019A Closer Look at Few-shot Classificationcited by 679
  7. 2017Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoverycited by 566
  8. 2019Generalizing from a Few Examples: A Survey on Few-Shot Learningcited by 462
  9. 2018Do Deep Generative Models Know What They Don't Know?cited by 443
  10. 2020Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?cited by 435
  11. 2020A Unifying Review of Deep and Shallow Anomaly Detectioncited by 423
  12. 2020Differentiable Augmentation for Data-Efficient GAN Trainingcited by 361
15 more
  1. 2019SinGAN: Learning a Generative Model from a Single Natural Imagecited by 348
  2. 2018Deep Anomaly Detection Using Geometric Transformationscited by 269
  3. 2020Patch SVDD: Patch-level SVDD for Anomaly Detection and Segmentationcited by 212
  4. 2020Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flowscited by 212
  5. 2020Classification-Based Anomaly Detection for General Datacited by 210
  6. 2016Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networkscited by 192
  7. 2019Deep Anomaly Detection with Deviation Networkscited by 152
  8. 2020DROCC: Deep Robust One-Class Classificationcited by 121
  9. 2016Deep Structured Energy Based Models for Anomaly Detectioncited by 113
  10. 2018Learning Representations of Ultrahigh-dimensional Data for Random Distance-based Outlier Detectioncited by 79
  11. 2018Non-Stationary Texture Synthesis by Adversarial Expansioncited by 66
  12. 2019Deep Weakly-supervised Anomaly Detectioncited by 59
  13. 2020Hierarchical Patch VAE-GAN: Generating Diverse Videos from a Single Samplecited by 43
  14. 2020Few-Shot One-Class Classification via Meta-Learningcited by 17
  15. 2019One-Way Prototypical Networkscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 7; 2023: 18; 2024: 16; 2025: 9; 2026: 6.

60 papers.

Sort:

By area:

  1. 2023WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentationcited by 311
  2. 2023Deep Industrial Image Anomaly Detection: A Surveycited by 147
  3. 2022Registration based Few-Shot Anomaly Detectioncited by 133
  4. 2024PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detectioncited by 97
  5. 2024Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detectioncited by 92
  6. 2024Toward Generalist Anomaly Detection via In-context Residual Learning with Few-shot Sample Promptscited by 88
  7. 2021Explainable Deep Few-shot Anomaly Detection with Deviation Networkscited by 69
  8. 2024Adapting Visual-Language Models for Generalizable Anomaly Detection in Medical Imagescited by 69
  9. 2023IM-IAD: Industrial Image Anomaly Detection Benchmark in Manufacturingcited by 64
  10. 2024SoftPatch: Unsupervised Anomaly Detection with Noisy Datacited by 55
  11. 2024Generalized Out-of-Distribution Detection and Beyond in Vision Language Model Era: A Surveycited by 36
  12. 2023ImbSAM: A Closer Look at Sharpness-Aware Minimization in Class-Imbalanced Recognitioncited by 31
38 more
  1. 2022MAEDAY: MAE for few and zero shot AnomalY-Detectioncited by 30
  2. 2025AdaptCLIP: Adapting CLIP for Universal Visual Anomaly Detectioncited by 28
  3. 2023Random Word Data Augmentation with CLIP for Zero-Shot Anomaly Detectioncited by 15
  4. 2025Deep Learning Advancements in Anomaly Detection: A Comprehensive Surveycited by 15
  5. 2024COFT-AD: COntrastive Fine-Tuning for Few-Shot Anomaly Detectioncited by 13
  6. 2022Teacher-Student Network for 3D Point Cloud Anomaly Detection with Few Normal Samplescited by 12
  7. 2024AMI-Net: Adaptive Mask Inpainting Network for Industrial Anomaly Detection and Localizationcited by 12
  8. 2025MultiADS: Defect-aware Supervision for Multi-type Anomaly Detection and Segmentation in Zero-Shot Learningcited by 12
  9. 2025MetaUAS: Universal Anomaly Segmentation with One-Prompt Meta-Learningcited by 12
  10. 2022A Survey of Visual Sensory Anomaly Detectioncited by 11
  11. 2024Text-Guided Variational Image Generation for Industrial Anomaly Detection and Segmentationcited by 11
  12. 2023Optimizing PatchCore for Few/many-shot Anomaly Detectioncited by 10
  13. 2025MadCLIP: Few-shot Medical Anomaly Detection with CLIPcited by 10
  14. 2023Image Synthesis under Limited Data: A Survey and Taxonomycited by 9
  15. 2025DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookupcited by 9
  16. 2023FewSOME: One-Class Few Shot Anomaly Detection with Siamese Networkscited by 8
  17. 2023What makes a good data augmentation for few-shot unsupervised image anomaly detection?cited by 8
  18. 2024Towards Zero-shot 3D Anomaly Localizationcited by 8
  19. 2023High-Fidelity Zero-Shot Texture Anomaly Localization Using Feature Correspondence Analysiscited by 7
  20. 2024SoftPatch+: Fully Unsupervised Anomaly Classification and Segmentationcited by 7
  21. 2024Few-Shot Anomaly Detection via Category-Agnostic Registration Learningcited by 6
  22. 2024AnomalySD: Few-Shot Multi-Class Anomaly Detection with Stable Diffusion Modelcited by 6
  23. 2021Anomaly Detection of Defect using Energy of Point Pattern Features within Random Finite Set Frameworkcited by 5
  24. 2023Instance-level Few-shot Learning with Class Hierarchy Miningcited by 5
  25. 2023Few-Shot Anomaly Detection with Adversarial Loss for Robust Feature Representationscited by 5
  26. 2021Out-of-Distribution Detection Without Class Labelscited by 4
  27. 2022Enhancing Few-shot Image Classification with Cosine Transformercited by 4
  28. 2026One Language-Free Foundation Model Is Enough for Universal Vision Anomaly Detectioncited by 4
  29. 2023That's BAD: Blind Anomaly Detection by Implicit Local Feature Clusteringcited by 3
  30. 2023Multi-Scale Memory Comparison for Zero-/Few-Shot Anomaly Detectioncited by 3
  31. 2023Quantile-based Maximum Likelihood Training for Outlier Detectioncited by 3
  32. 2026Dual Distillation for Few-Shot Anomaly Detectioncited by 3
  33. 2021FROB: Few-shot ROBust Model for Classification and Out-of-Distribution Detectioncited by 2
  34. 2022Discriminative Feature Learning Framework with Gradient Preference for Anomaly Detectioncited by 2
  35. 2023Few-shot Weakly-supervised Cybersecurity Anomaly Detectioncited by 2
  36. 2024SOWA: Adapting Hierarchical Frozen Window Self-Attention to Visual-Language Models for Better Anomaly Detectioncited by 2
  37. 2025Prototypical Learning Guided Context-Aware Segmentation Network for Few-Shot Anomaly Detectioncited by 2
  38. 2022Convolutional Ensembling based Few-Shot Defect Detection Techniquecited by 1

50 most cited of 60 All 60 (JSON)