{
  "id": "2504.11895",
  "version": "v2",
  "published": "2025-04-16T09:21:34.000Z",
  "updated": "2025-05-08T09:24:41.000Z",
  "title": "Search is All You Need for Few-shot Anomaly Detection",
  "authors": [
    "Qishan Wang",
    "Jia Guo",
    "Shuyong Gao",
    "Haofen Wang",
    "Li Xiong",
    "Junjie Hu",
    "Hanqi Guo",
    "Wenqiang Zhang"
  ],
  "categories": [
    "cs.CV"
  ],
  "abstract": "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.",
  "revisions": [
    {
      "version": "v2",
      "updated": "2025-05-08T09:24:41.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "few-shot anomaly detection",
      "employ multi-modal foundation models",
      "demonstrate visionads exceptional performance",
      "benchmarks demonstrate visionads exceptional",
      "efficient one-for-all multi-class detection"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}