Zero-shot anomaly detection aims to detect and localise abnormal regions in the image without access to any in-domain training images. While recent approaches leverage vision-language models (VLMs), such as CLIP, to transfer high-level concept knowledge, methods based on purely vision foundation models (VFMs), like DINOv2, have lagged behind in performance. We argue that this gap stems from two practical issues: (i) limited diversity in existing auxiliary anomaly detection datasets and (ii) overly shallow VFM adaptation strategies. To address both challenges, we propose AnomalyVFM, a general and effective framework that turns any pretrained VFM into a strong zero-shot anomaly detector. Our approach combines a robust three-stage synthetic dataset generation scheme with a parameter-efficient adaptation mechanism, utilising low-rank feature adapters and a confidence-weighted pixel loss. Together, these components enable modern VFMs to substantially outperform current state-of-the-art methods. More specifically, with RADIO as a backbone, AnomalyVFM achieves an average image-level AUROC of 94.1% across 9 diverse datasets, surpassing previous methods by significant 3.3 percentage points. Project Page: https://maticfuc.github.io/anomaly_vfm/

翻译：零样本异常检测旨在无需访问任何域内训练图像的情况下，检测并定位图像中的异常区域。尽管近期方法利用视觉-语言模型（如CLIP）来迁移高层概念知识，但基于纯视觉基础模型（如DINOv2）的方法在性能上仍处于落后地位。我们认为这种差距源于两个实际问题：（i）现有辅助异常检测数据集的多样性有限；（ii）视觉基础模型的适应策略过于浅层。为应对这两项挑战，我们提出AnomalyVFM——一个通用且高效的框架，可将任何预训练的视觉基础模型转化为强大的零样本异常检测器。该方法结合了鲁棒的三阶段合成数据集生成方案与参数高效的适应机制，利用低秩特征适配器和置信度加权的像素损失。这些组件共同使现代视觉基础模型能够显著超越当前最先进方法。具体而言，以RADIO为骨干网络时，AnomalyVFM在9个多样化数据集上实现了94.1%的平均图像级AUROC，较先前方法提升3.3个百分点。项目页面：https://maticfuc.github.io/anomaly_vfm/