mlsanityData to 7 Oct 2026

Few-Shot Anomaly Detection via Category-Agnostic Registration Learning

arXiv 2406.08810 ↗First posted 13 Jun 2024cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Most existing anomaly detection (AD) methods require a dedicated model for each category. Such a paradigm, despite its promising results, is computationally expensive and inefficient, thereby failing to meet the requirements for realworld applications. Inspired by how humans detect anomalies, by comparing a query image to known normal ones, this article proposes a novel few-shot AD (FSAD) framework. Using a training set of normal images from various categories, registration, aiming to align normal images of the same categories, is leveraged as the proxy task for self-supervised category-agnostic representation learning. At test time, an image and its corresponding support set, consisting of a few normal images from the same category, are supplied, and anomalies are identified by comparing the registered features of the test image to its corresponding support image features. Such a setup enables the model to generalize to novel test categories. It is, to our best knowledge, the first FSAD method that requires no model fine-tuning for novel categories: enabling a single model to be applied to all categories. Extensive experiments demonstrate the effectiveness of the proposed method. Particularly, it improves the current state-of-the-art (SOTA) for FSAD by 11.3% and 8.3% on the MVTec and MPDD benchmarks, respectively. The source code is available at https://github.com/Haoyan-Guan/CAReg.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 47 of its 91 references that are in the map. First posted on arXiv 13 Jun 2024.

Builds on

47 of 91 references.

References · 47

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  4. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  5. 2020Exploring Simple Siamese Representation Learningcited by 2,853
  6. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,586
  7. 2015Spatial Transformer Networkscited by 1,423
  8. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,379
  9. 2015Unsupervised Visual Representation Learning by Context Predictioncited by 1,062
  10. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 772
  11. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 596
  12. 2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 591
35 more
  1. 2017Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoverycited by 566
  2. 2019Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detectioncited by 560
  3. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 529
  4. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  5. 2018GANomaly: Semi-Supervised Anomaly Detection via Adversarial Trainingcited by 409
  6. 2019Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddingscited by 386
  7. 2021CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flowscited by 320
  8. 2020Multiresolution Knowledge Distillation for Anomaly Detectioncited by 285
  9. 2018Deep Anomaly Detection Using Geometric Transformationscited by 269
  10. 2020Patch SVDD: Patch-level SVDD for Anomaly Detection and Segmentationcited by 212
  11. 2020Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flowscited by 212
  12. 2018Adversarially Learned One-Class Classifier for Novelty Detectioncited by 202
  13. 2021Free Lunch for Few-shot Learning: Distribution Calibrationcited by 165
  14. 2022Registration based Few-Shot Anomaly Detectioncited by 133
  15. 2020A Survey of Single-Scene Video Anomaly Detectioncited by 88
  16. 2021Repurposing GANs for One-shot Semantic Part Segmentationcited by 88
  17. 2020A Background-Agnostic Framework with Adversarial Training for Abnormal Event Detection in Videocited by 85
  18. 2021Pixel-wise Energy-biased Abstention Learning for Anomaly Segmentation on Complex Urban Driving Scenescited by 83
  19. 2021A Hierarchical Transformation-Discriminating Generative Model for Few Shot Anomaly Detectioncited by 60
  20. 2022Self-Supervised Masking for Unsupervised Anomaly Detection and Localizationcited by 43
  21. 2020Robust Unsupervised Video Anomaly Detection by Multi-Path Frame Predictioncited by 42
  22. 2021Anomaly Detection of Time Series with Smoothness-Inducing Sequential Variational Auto-Encodercited by 39
  23. 2021Focus Your Distribution: Coarse-to-Fine Non-Contrastive Learning for Anomaly Detection and Localizationcited by 32
  24. 2021Semi-orthogonal Embedding for Efficient Unsupervised Anomaly Segmentationcited by 26
  25. 2021Adversarially Robust One-class Novelty Detectioncited by 24
  26. 2020Few-Shot One-Class Classification via Meta-Learningcited by 17
  27. 2016Coherence Pursuit: Fast, Simple, and Robust Principal Component Analysiscited by 13
  28. 2020Few-Shot Learning with Geometric Constraintscited by 13
  29. 2020Graph Regularized Autoencoder and its Application in Unsupervised Anomaly Detectioncited by 11
  30. 2018Real-Time Nonparametric Anomaly Detection in High-Dimensional Settingscited by 10
  31. 2020OneFlow: One-class flow for anomaly detection based on a minimal volume regioncited by 9
  32. 2020ESAD: End-to-end Deep Semi-supervised Anomaly Detectioncited by 8
  33. 2021Bayesian Embeddings for Few-Shot Open World Recognitioncited by 8
  34. 2023Few-Shot Anomaly Detection with Adversarial Loss for Robust Feature Representationscited by 5
  35. 2022Query Semantic Reconstruction for Background in Few-Shot Segmentationcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 5; 2026: 1.

6 papers.

  1. 2025Foundation Visual Encoders Are Secretly Few-Shot Anomaly Detectorscited by 5
  2. 2025A Comprehensive Survey for Real-World Industrial Defect Detection: Challenges, Approaches, and Prospectscited by 2
  3. 2025Prototypical Learning Guided Context-Aware Segmentation Network for Few-Shot Anomaly Detectioncited by 2
  4. 2025Visual Anomaly Detection for Reliable Robotic Implantation of Flexible Microelectrode Arraycited by 0
  5. 2025Quantized FCA: Efficient Zero-Shot Texture Anomaly Detectioncited by 0
  6. 2026PADFormer: Pose-agnostic Anomaly Detection from Sparse View Imagescited by 0