用预训练视觉模型检测异常，少样本下表现优异。
Foundation Visual Encoders Are Secretly Few-Shot Anomaly Detectors
- 通过非线性投影学习自然图像流形，捕捉正常分布特征。
- 仅用少量样本即可实现多类异常检测，参数量远低于以往方法。
- 适用于工业质检等场景，对DINOv3等主流模型均有效。
少样本异常检测简化了工业安全检查流程，但样本有限导致正常与异常特征区分困难，尤其在无类别先验条件下更难。大规模预训练的视觉基础模型通过海量数据学习到正常图像的通用分布。我们发现图像中异常程度与学习到的嵌入差异直接相关，据此设计名为FoundAD的少样本异常检测器。该方法通过学习一个非线性投影算子，将其映射到自然图像流形上，能有效表征并识别图像中的分布外区域。大量实验表明，本方法支持多类别检测，在参数量显著减少的情况下仍达到有竞争力的性能。基于多个基础编码器（包括新推出的DINOv3）的评估验证了该思路的普适性，拓展了对基础特征的理解，推动了少样本异常检测的发展。
原文摘要 · Abstract (English)
Few-shot anomaly detection streamlines and simplifies industrial safety inspection. However, limited samples make accurate differentiation between normal and abnormal features challenging, and even more so under category-agnostic conditions. Large-scale pre-training of foundation visual encoders has advanced many fields, as the enormous quantity of data helps to learn the general distribution of normal images. We observe that the anomaly amount in an image directly correlates with the difference in the learnt embeddings and utilize this to design a few-shot anomaly detector termed FoundAD. This is done by learning a nonlinear projection operator onto the natural image manifold. The simple operator acts as an effective tool for anomaly detection to characterize and identify out-of-distribution regions in an image. Extensive experiments show that our approach supports multi-class detection and achieves competitive performance while using substantially fewer parameters than prior methods. Backed up by evaluations with multiple foundation encoders, including fresh DINOv3, we believe this idea broadens the perspective on foundation features and advances the field of few-shot anomaly detection.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。