AnomalyDINO: Boosting Patch-based Few-shot Anomaly Detection with DINOv2

2024/05/23 by Simon Damm, Damm, Simon, Mike Laszkiewicz +5 · 10 citations
Computer Science · Medicine · #Anomaly Detection Techniques and Applications #COVID-19 diagnosis using AI #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences

paper · pdf · doi:10.48550/arxiv.2405.14529

openalex publication_date 2024/05/23 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Recent advances in multimodal foundation models have set new standards in few-shot anomaly detection. This paper explores whether high-quality visual features alone are sufficient to rival existing state-of-the-art vision-language models. We affirm this by adapting DINOv2 for one-shot and few-shot anomaly detection, with a focus on industrial applications. We show that this approach does not only rival existing techniques but can even outmatch them in many settings. Our proposed vision-only approach, AnomalyDINO, follows the well-established patch-level deep nearest neighbor paradigm, and enables both image-level anomaly prediction and pixel-level anomaly segmentation. The approach is methodologically simple and training-free and, thus, does not require any additional data for fine-tuning or meta-learning. The approach is methodologically simple and training-free and, thus, does not require any additional data for fine-tuning or meta-learning. Despite its simplicity, AnomalyDINO achieves state-of-the-art results in one- and few-shot anomaly detection (e.g., pushing the one-shot performance on MVTec-AD from an AUROC of 93.1% to 96.6%). The reduced overhead, coupled with its outstanding few-shot performance, makes AnomalyDINO a strong candidate for fast deployment, e.g., in industrial contexts.

Cited by

• DuoAD: Leveraging [CLS] Dual Characteristics for Training-Free Few-Shot Anomaly Detection
• UniADC: A Unified Framework for Anomaly Detection and Classification
• Image-Intrinsic Priors for Integrated Circuit Defect Detection and Novel Class Discovery via Self-Supervised Learning
• Towards Adversarial Robustness and Uncertainty Quantification in DINOv2-based Few-Shot Anomaly Detection
• Foundation Visual Encoders Are Secretly Few-Shot Anomaly Detectors
• Normal-Abnormal Guided Generalist Anomaly Detection
• PatchEAD: Unifying Industrial Visual Prompting Frameworks for Patch-Exclusive Anomaly Detection
• Anomaly Detection by Clustering DINO Embeddings using a Dirichlet Process Mixture
• Leveraging Intermediate Representations of Time Series Foundation Models for Anomaly Detection
• SegDINO: An Efficient Design for Medical and Natural Image Segmentation with DINO-V3
• Self-Navigated Residual Mamba for Universal Industrial Anomaly Detection
• Anomalous Samples for Few-Shot Anomaly Detection

Related

• Foundation Visual Encoders Are Secretly Few-Shot Anomaly Detectors
• FADE: Few-shot/zero-shot Anomaly Detection Engine using Large Vision-Language Model
• AD-DINOv3: Enhancing DINOv3 for Zero-Shot Anomaly Detection with Anomaly-Aware Calibration
• Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection
• PatchProto Networks for Few-shot Visual Anomaly Classification