mlsanityData to 14 Oct 2026

Optimizing PatchCore for Few/many-shot Anomaly Detection

arXiv 2307.10792 ↗First posted 20 Jul 2023cs.CV cs.AI cs.LGcited by 10

Not on the map. Why?

Abstract (arXiv)

Few-shot anomaly detection (AD) is an emerging sub-field of general AD, and tries to distinguish between normal and anomalous data using only few selected samples. While newly proposed few-shot AD methods do compare against pre-existing algorithms developed for the full-shot domain as baselines, they do not dedicatedly optimize them for the few-shot setting. It thus remains unclear if the performance of such pre-existing algorithms can be further improved. We address said question in this work. Specifically, we present a study on the AD/anomaly segmentation (AS) performance of PatchCore, the current state-of-the-art full-shot AD/AS algorithm, in both the few-shot and the many-shot settings. We hypothesize that further performance improvements can be realized by (I) optimizing its various hyperparameters, and by (II) transferring techniques known to improve few-shot supervised learning to the AD domain. Exhaustive experiments on the public VisA and MVTec AD datasets reveal that (I) significant performance improvements can be realized by optimizing hyperparameters such as the underlying feature extractor, and that (II) image-level augmentations can, but are not guaranteed, to improve performance. Based on these findings, we achieve a new state of the art in few-shot AD on VisA, further demonstrating the merit of adapting pre-existing AD/AS methods to the few-shot setting. Last, we identify the investigation of feature extractors with a strong inductive bias as a potential future research direction for (few-shot) AD/AS.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 41 of its 63 references that are in the map. First posted on arXiv 20 Jul 2023.

Builds on

41 of 63 references.

References · 41

  1. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  2. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  3. 2022A ConvNet for the 2020scited by 3,579
  4. 2016Wide Residual Networkscited by 3,070
  5. 2021EfficientNetV2: Smaller Models and Faster Trainingcited by 1,135
  6. 2018Reconciling modern machine learning practice and the bias-variance trade-offcited by 927
  7. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 776
  8. 2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 594
  9. 2018Do Better ImageNet Models Transfer Better?cited by 565
  10. 2018Albumentations: fast and flexible image augmentationscited by 560
  11. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 514
  12. 2020A Unifying Review of Deep and Shallow Anomaly Detectioncited by 425
29 more
  1. 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 400
  2. 2019Making Convolutional Networks Shift-Invariant Againcited by 391
  3. 2020Semi-Supervised Semantic Segmentation with Cross-Consistency Trainingcited by 376
  4. 2017The Effectiveness of Data Augmentation in Image Classification using Deep Learningcited by 370
  5. 2015Understanding Neural Networks Through Deep Visualizationcited by 334
  6. 2023WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentationcited by 315
  7. 2020Sub-Image Anomaly Detection with Deep Pyramid Correspondencescited by 300
  8. 2020Patch SVDD: Patch-level SVDD for Anomaly Detection and Segmentationcited by 212
  9. 2020Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flowscited by 212
  10. 2019Fixing the train-test resolution discrepancycited by 209
  11. 2017Learning Steerable Filters for Rotation Equivariant CNNscited by 194
  12. 2022Registration based Few-Shot Anomaly Detectioncited by 133
  13. 2023APRIL-GAN: A Zero-/Few-Shot Anomaly Classification and Segmentation Method for CVPR 2023 VAND Workshop Challenge Tracks 1&2: 1st Place on Zero-shot AD and 4th Place on Few-shot ADcited by 130
  14. 2022Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Differencecited by 126
  15. 2020Modeling the Distribution of Normal Data in Pre-Trained Deep Features for Anomaly Detectioncited by 115
  16. 2021A Survey on Data Augmentation for Text Classificationcited by 111
  17. 2022Anomalib: A Deep Learning Library for Anomaly Detectioncited by 75
  18. 2023Pushing the Limits of Fewshot Anomaly Detection in Industry Vision: Graphcorecited by 75
  19. 2020Regularizing Deep Networks with Semantic Data Augmentationcited by 73
  20. 2023IM-IAD: Industrial Image Anomaly Detection Benchmark in Manufacturingcited by 64
  21. 2021A Hierarchical Transformation-Discriminating Generative Model for Few Shot Anomaly Detectioncited by 60
  22. 2023Segment Any Anomaly without Training via Hybrid Prompt Regularizationcited by 60
  23. 2023E(2)-Equivariant Vision Transformercited by 27
  24. 2018Are pre-trained CNNs good feature extractors for anomaly detection in surveillance videos?cited by 17
  25. 2021Blending Anti-Aliasing into Vision Transformercited by 16
  26. 2023Alias-Free Convnets: Fractional Shift Invariance via Polynomial Activationscited by 11
  27. 2022Fast Bayesian Coresets via Subsampling and Quasi-Newton Refinementcited by 9
  28. 2023What makes a good data augmentation for few-shot unsupervised image anomaly detection?cited by 8
  29. 2021Data augmentation and pre-trained networks for extremely low data regimes unsupervised visual inspectioncited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 5; 2025: 2; 2026: 2.

10 papers.

  1. 2024AnomalyDINO: Boosting Patch-based Few-shot Anomaly Detection with DINOv2cited by 53
  2. 2024Dual-path Frequency Discriminators for Few-shot Anomaly Detectioncited by 7
  3. 2025FastRef:Fast Prototype Refinement for Few-Shot Industrial Anomaly Detectioncited by 7
  4. 2026SubspaceAD: Training-Free Few-Shot Anomaly Detection via Subspace Modelingcited by 7
  5. 2024Small Object Few-shot Segmentation for Vision-based Industrial Inspectioncited by 5
  6. 2024CableInspect-AD: An Expert-Annotated Anomaly Detection Datasetcited by 5
  7. 2024Leveraging Unsupervised Learning for Cost-Effective Visual Anomaly Detectioncited by 1
  8. 2023PatchProto Networks for Few-shot Visual Anomaly Classificationcited by 0
  9. 2025Bridge Feature Matching and Cross-Modal Alignment with Mutual-filtering for Zero-shot Anomaly Detectioncited by 0
  10. 2026ConceptADapt: Concept-guided Adaptive Feature Reconstruction with Dynamic Attention for Few-Shot Industrial Anomaly Detectioncited by 0