Search is All You Need for Few-shot Anomaly Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Qishan, Guo, Jia, Gao, Shuyong, Wang, Haofen, Xiong, Li, Hu, Junjie, Guo, Hanqi, Zhang, Wenqiang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908353454669824
author Wang, Qishan
Guo, Jia
Gao, Shuyong
Wang, Haofen
Xiong, Li
Hu, Junjie
Guo, Hanqi
Zhang, Wenqiang
author_facet Wang, Qishan
Guo, Jia
Gao, Shuyong
Wang, Haofen
Xiong, Li
Hu, Junjie
Guo, Hanqi
Zhang, Wenqiang
contents Few-shot anomaly detection (FSAD) has emerged as a crucial yet challenging task in industrial inspection, where normal distribution modeling must be accomplished with only a few normal images. While existing approaches typically employ multi-modal foundation models combining language and vision modalities for prompt-guided anomaly detection, these methods often demand sophisticated prompt engineering and extensive manual tuning. In this paper, we demonstrate that a straightforward nearest-neighbor search framework can surpass state-of-the-art performance in both single-class and multi-class FSAD scenarios. Our proposed method, VisionAD, consists of four simple yet essential components: (1) scalable vision foundation models that extract universal and discriminative features; (2) dual augmentation strategies - support augmentation to enhance feature matching adaptability and query augmentation to address the oversights of single-view prediction; (3) multi-layer feature integration that captures both low-frequency global context and high-frequency local details with minimal computational overhead; and (4) a class-aware visual memory bank enabling efficient one-for-all multi-class detection. Extensive evaluations across MVTec-AD, VisA, and Real-IAD benchmarks demonstrate VisionAD's exceptional performance. Using only 1 normal images as support, our method achieves remarkable image-level AUROC scores of 97.4%, 94.8%, and 70.8% respectively, outperforming current state-of-the-art approaches by significant margins (+1.6%, +3.2%, and +1.4%). The training-free nature and superior few-shot capabilities of VisionAD make it particularly appealing for real-world applications where samples are scarce or expensive to obtain. Code is available at https://github.com/Qiqigeww/VisionAD.
format Preprint
id arxiv_https___arxiv_org_abs_2504_11895
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Search is All You Need for Few-shot Anomaly Detection
Wang, Qishan
Guo, Jia
Gao, Shuyong
Wang, Haofen
Xiong, Li
Hu, Junjie
Guo, Hanqi
Zhang, Wenqiang
Computer Vision and Pattern Recognition
Few-shot anomaly detection (FSAD) has emerged as a crucial yet challenging task in industrial inspection, where normal distribution modeling must be accomplished with only a few normal images. While existing approaches typically employ multi-modal foundation models combining language and vision modalities for prompt-guided anomaly detection, these methods often demand sophisticated prompt engineering and extensive manual tuning. In this paper, we demonstrate that a straightforward nearest-neighbor search framework can surpass state-of-the-art performance in both single-class and multi-class FSAD scenarios. Our proposed method, VisionAD, consists of four simple yet essential components: (1) scalable vision foundation models that extract universal and discriminative features; (2) dual augmentation strategies - support augmentation to enhance feature matching adaptability and query augmentation to address the oversights of single-view prediction; (3) multi-layer feature integration that captures both low-frequency global context and high-frequency local details with minimal computational overhead; and (4) a class-aware visual memory bank enabling efficient one-for-all multi-class detection. Extensive evaluations across MVTec-AD, VisA, and Real-IAD benchmarks demonstrate VisionAD's exceptional performance. Using only 1 normal images as support, our method achieves remarkable image-level AUROC scores of 97.4%, 94.8%, and 70.8% respectively, outperforming current state-of-the-art approaches by significant margins (+1.6%, +3.2%, and +1.4%). The training-free nature and superior few-shot capabilities of VisionAD make it particularly appealing for real-world applications where samples are scarce or expensive to obtain. Code is available at https://github.com/Qiqigeww/VisionAD.
title Search is All You Need for Few-shot Anomaly Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.11895