AnomalyVFM——将视觉基础模型转化为零样本异常检测器
AnomalyVFM -- Transforming Vision Foundation Models into Zero-Shot Anomaly Detectors
把任意预训练视觉基础模型（如 DINOv2、RADIO）通过低秩特征适配器加置信度加权像素损失改造成零样本异常检测器，并给出三阶段合成异常数据生成方案，可直接复用于工业质检等无监督缺陷定位场景。
原文依据 we propose AnomalyVFM, a general and effective framework that turns any pretrained VFM into a strong zero-shot anomaly detector
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论零样本异常检测旨在无需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。尽管近期方法借助视觉语言模型（如 CLIP）迁移高层概念知识，但基于纯视觉基础模型（如 DINOv2）的方法在性能上仍显落后。我们认为这一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）视觉基础模型的适配策略过于浅层。为应对这两项挑战，我们提出 AnomalyVFM，一个通用且有效的框架，可将任意预训练视觉基础模型转化为强零样本异常检测器。该方法将稳健的三阶段合成数据集生成方案与参数高效适配机制相结合，采用低秩特征适配器和置信度加权像素损失。这些组件共同使现代视觉基础模型显著超越当前最优方法。具体而言，以 RADIO 为骨干时，AnomalyVFM 在 9 个多样化数据集上取得 94.1% 的平均图像级 AUROC，较此前方法显著提升 3.3 个百分点。代码：https://maticfuc.github.io/anomaly_vfm/ 项目主页
英文原文摘要 1265 字符
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. Code: \href https://maticfuc.github.io/anomaly_vfm/ Project Page