# Optimizing PatchCore for Few/many-shot Anomaly Detection

arXiv: https://arxiv.org/abs/2307.10792 · HTML: https://mlsanity.com/paper/2307.10792/

## 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 (most cited first, 30 of 41)

- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [EfficientNetV2: Smaller Models and Faster Training](https://mlsanity.com/paper/2104.00298/) (2021)
- [Reconciling modern machine learning practice and the bias-variance trade-off](https://mlsanity.com/paper/1812.11118/) (2018)
- [Towards Total Recall in Industrial Anomaly Detection](https://mlsanity.com/paper/2106.08265/) (2021)
- [PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localization](https://mlsanity.com/paper/2011.08785/) (2020)
- [Do Better ImageNet Models Transfer Better?](https://mlsanity.com/paper/1805.08974/) (2018)
- [Albumentations: fast and flexible image augmentations](https://mlsanity.com/paper/1809.06839/) (2018)
- [DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detection](https://mlsanity.com/paper/2108.07610/) (2021)
- [A Unifying Review of Deep and Shallow Anomaly Detection](https://mlsanity.com/paper/2009.11732/) (2020)
- [SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentation](https://mlsanity.com/paper/2207.14315/) (2022)
- [Making Convolutional Networks Shift-Invariant Again](https://mlsanity.com/paper/1904.11486/) (2019)
- [Semi-Supervised Semantic Segmentation with Cross-Consistency Training](https://mlsanity.com/paper/2003.09005/) (2020)
- [The Effectiveness of Data Augmentation in Image Classification using Deep Learning](https://mlsanity.com/paper/1712.04621/) (2017)
- [Understanding Neural Networks Through Deep Visualization](https://mlsanity.com/paper/1506.06579/) (2015)
- [WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation](https://mlsanity.com/paper/2303.14814/) (2023)
- [Sub-Image Anomaly Detection with Deep Pyramid Correspondences](https://mlsanity.com/paper/2005.02357/) (2020)
- [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)
- [Fixing the train-test resolution discrepancy](https://mlsanity.com/paper/1906.06423/) (2019)
- [Learning Steerable Filters for Rotation Equivariant CNNs](https://mlsanity.com/paper/1711.07289/) (2017)
- [Registration based Few-Shot Anomaly Detection](https://mlsanity.com/paper/2207.07361/) (2022)
- [APRIL-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 AD](https://mlsanity.com/paper/2305.17382/) (2023)
- [Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference](https://mlsanity.com/paper/2204.07305/) (2022)
- [Modeling the Distribution of Normal Data in Pre-Trained Deep Features for Anomaly Detection](https://mlsanity.com/paper/2005.14140/) (2020)
- [A Survey on Data Augmentation for Text Classification](https://mlsanity.com/paper/2107.03158/) (2021)
- [Anomalib: A Deep Learning Library for Anomaly Detection](https://mlsanity.com/paper/2202.08341/) (2022)
- [Pushing the Limits of Fewshot Anomaly Detection in Industry Vision: Graphcore](https://mlsanity.com/paper/2301.12082/) (2023)

## Built on by (most cited first, 10 of 10)

- [AnomalyDINO: Boosting Patch-based Few-shot Anomaly Detection with DINOv2](https://mlsanity.com/paper/2405.14529/) (2024)
- [Dual-path Frequency Discriminators for Few-shot Anomaly Detection](https://mlsanity.com/paper/2403.04151/) (2024)
- [FastRef:Fast Prototype Refinement for Few-Shot Industrial Anomaly Detection](https://mlsanity.com/paper/2506.21398/) (2025)
- [SubspaceAD: Training-Free Few-Shot Anomaly Detection via Subspace Modeling](https://mlsanity.com/paper/2602.23013/) (2026)
- [Small Object Few-shot Segmentation for Vision-based Industrial Inspection](https://mlsanity.com/paper/2407.21351/) (2024)
- [CableInspect-AD: An Expert-Annotated Anomaly Detection Dataset](https://mlsanity.com/paper/2409.20353/) (2024)
- [Leveraging Unsupervised Learning for Cost-Effective Visual Anomaly Detection](https://mlsanity.com/paper/2409.15980/) (2024)
- [PatchProto Networks for Few-shot Visual Anomaly Classification](https://mlsanity.com/paper/2310.04688/) (2023)
- [Bridge Feature Matching and Cross-Modal Alignment with Mutual-filtering for Zero-shot Anomaly Detection](https://mlsanity.com/paper/2507.11003/) (2025)
- [ConceptADapt: Concept-guided Adaptive Feature Reconstruction with Dynamic Attention for Few-Shot Industrial Anomaly Detection](https://mlsanity.com/paper/2608.05743/) (2026)

## 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.