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

arXiv: https://arxiv.org/abs/2104.14535 · HTML: https://mlsanity.com/paper/2104.14535/

## Key facts

- Cited by 60 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 45 references that are in the map.
- First posted on arXiv 29 Apr 2021.

## Builds on (most cited first, 27 of 27)

- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Training Generative Adversarial Networks with Limited Data](https://mlsanity.com/paper/2006.06676/) (2020)
- [Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks](https://mlsanity.com/paper/1703.10593/) (2017)
- [A Closer Look at Few-shot Classification](https://mlsanity.com/paper/1904.04232/) (2019)
- [Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery](https://mlsanity.com/paper/1703.05921/) (2017)
- [Generalizing from a Few Examples: A Survey on Few-Shot Learning](https://mlsanity.com/paper/1904.05046/) (2019)
- [Do Deep Generative Models Know What They Don't Know?](https://mlsanity.com/paper/1810.09136/) (2018)
- [Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?](https://mlsanity.com/paper/2003.11539/) (2020)
- [A Unifying Review of Deep and Shallow Anomaly Detection](https://mlsanity.com/paper/2009.11732/) (2020)
- [Differentiable Augmentation for Data-Efficient GAN Training](https://mlsanity.com/paper/2006.10738/) (2020)
- [SinGAN: Learning a Generative Model from a Single Natural Image](https://mlsanity.com/paper/1905.01164/) (2019)
- [Deep Anomaly Detection Using Geometric Transformations](https://mlsanity.com/paper/1805.10917/) (2018)
- [Patch SVDD: Patch-level SVDD for Anomaly Detection and Segmentation](https://mlsanity.com/paper/2006.16067/) (2020)
- [Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flows](https://mlsanity.com/paper/2008.12577/) (2020)
- [Classification-Based Anomaly Detection for General Data](https://mlsanity.com/paper/2005.02359/) (2020)
- [Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networks](https://mlsanity.com/paper/1604.04382/) (2016)
- [Deep Anomaly Detection with Deviation Networks](https://mlsanity.com/paper/1911.08623/) (2019)
- [DROCC: Deep Robust One-Class Classification](https://mlsanity.com/paper/2002.12718/) (2020)
- [Deep Structured Energy Based Models for Anomaly Detection](https://mlsanity.com/paper/1605.07717/) (2016)
- [Learning Representations of Ultrahigh-dimensional Data for Random Distance-based Outlier Detection](https://mlsanity.com/paper/1806.04808/) (2018)
- [Non-Stationary Texture Synthesis by Adversarial Expansion](https://mlsanity.com/paper/1805.04487/) (2018)
- [Deep Weakly-supervised Anomaly Detection](https://mlsanity.com/paper/1910.13601/) (2019)
- [Hierarchical Patch VAE-GAN: Generating Diverse Videos from a Single Sample](https://mlsanity.com/paper/2006.12226/) (2020)
- [Few-Shot One-Class Classification via Meta-Learning](https://mlsanity.com/paper/2007.04146/) (2020)
- [One-Way Prototypical Networks](https://mlsanity.com/paper/1906.00820/) (2019)

## Built on by (most cited first, 30 of 60)

- [WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation](https://mlsanity.com/paper/2303.14814/) (2023)
- [Deep Industrial Image Anomaly Detection: A Survey](https://mlsanity.com/paper/2301.11514/) (2023)
- [Registration based Few-Shot Anomaly Detection](https://mlsanity.com/paper/2207.07361/) (2022)
- [PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detection](https://mlsanity.com/paper/2404.05231/) (2024)
- [Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection](https://mlsanity.com/paper/2405.14325/) (2024)
- [Toward Generalist Anomaly Detection via In-context Residual Learning with Few-shot Sample Prompts](https://mlsanity.com/paper/2403.06495/) (2024)
- [Explainable Deep Few-shot Anomaly Detection with Deviation Networks](https://mlsanity.com/paper/2108.00462/) (2021)
- [Adapting Visual-Language Models for Generalizable Anomaly Detection in Medical Images](https://mlsanity.com/paper/2403.12570/) (2024)
- [IM-IAD: Industrial Image Anomaly Detection Benchmark in Manufacturing](https://mlsanity.com/paper/2301.13359/) (2023)
- [SoftPatch: Unsupervised Anomaly Detection with Noisy Data](https://mlsanity.com/paper/2403.14233/) (2024)
- [Generalized Out-of-Distribution Detection and Beyond in Vision Language Model Era: A Survey](https://mlsanity.com/paper/2407.21794/) (2024)
- [ImbSAM: A Closer Look at Sharpness-Aware Minimization in Class-Imbalanced Recognition](https://mlsanity.com/paper/2308.07815/) (2023)
- [MAEDAY: MAE for few and zero shot AnomalY-Detection](https://mlsanity.com/paper/2211.14307/) (2022)
- [AdaptCLIP: Adapting CLIP for Universal Visual Anomaly Detection](https://mlsanity.com/paper/2505.09926/) (2025)
- [Deep Learning Advancements in Anomaly Detection: A Comprehensive Survey](https://mlsanity.com/paper/2503.13195/) (2025)
- [Random Word Data Augmentation with CLIP for Zero-Shot Anomaly Detection](https://mlsanity.com/paper/2308.11119/) (2023)
- [COFT-AD: COntrastive Fine-Tuning for Few-Shot Anomaly Detection](https://mlsanity.com/paper/2402.18998/) (2024)
- [MetaUAS: Universal Anomaly Segmentation with One-Prompt Meta-Learning](https://mlsanity.com/paper/2505.09265/) (2025)
- [Teacher-Student Network for 3D Point Cloud Anomaly Detection with Few Normal Samples](https://mlsanity.com/paper/2210.17258/) (2022)
- [AMI-Net: Adaptive Mask Inpainting Network for Industrial Anomaly Detection and Localization](https://mlsanity.com/paper/2412.11802/) (2024)
- [MultiADS: Defect-aware Supervision for Multi-type Anomaly Detection and Segmentation in Zero-Shot Learning](https://mlsanity.com/paper/2504.06740/) (2025)
- [A Survey of Visual Sensory Anomaly Detection](https://mlsanity.com/paper/2202.07006/) (2022)
- [Text-Guided Variational Image Generation for Industrial Anomaly Detection and Segmentation](https://mlsanity.com/paper/2403.06247/) (2024)
- [Optimizing PatchCore for Few/many-shot Anomaly Detection](https://mlsanity.com/paper/2307.10792/) (2023)
- [MadCLIP: Few-shot Medical Anomaly Detection with CLIP](https://mlsanity.com/paper/2506.23810/) (2025)
- [DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup](https://mlsanity.com/paper/2508.13560/) (2025)
- [Image Synthesis under Limited Data: A Survey and Taxonomy](https://mlsanity.com/paper/2307.16879/) (2023)
- [FewSOME: One-Class Few Shot Anomaly Detection with Siamese Networks](https://mlsanity.com/paper/2301.06957/) (2023)
- [What makes a good data augmentation for few-shot unsupervised image anomaly detection?](https://mlsanity.com/paper/2304.03294/) (2023)
- [Towards Zero-shot 3D Anomaly Localization](https://mlsanity.com/paper/2412.04304/) (2024)

## 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.