RAID：检索增强的异常检测
RAID: Retrieval-Augmented Anomaly Detection
把 RAG 的「检索样本直接参与生成」思路搬到异常图生成上：用分层向量库检索类/语义/实例级正常模板，再用匹配代价体与引导式 MoE 抑制匹配噪声，可作为工业缺陷检测与少样本异常定位的可复用范式。
原文依据 we focus on using retrieved normal samples to guide noise suppression in anomaly map generation
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论无监督异常检测（UAD）旨在通过建立测试图像与正常模板之间的对应关系来识别异常区域。现有方法主要依赖图像重建或模板检索，但面临一个根本性挑战：测试图像与正常模板之间的匹配不可避免地会因类内差异、不完美的对应关系以及模板数量有限而引入噪声。观察到检索增强生成（RAG）在生成过程中直接利用检索到的样本，我们从这个视角重新审视 UAD，并提出 RAID，一个面向抗噪异常检测与定位的检索增强 UAD 框架。与标准 RAG 用于丰富上下文或知识不同，我们专注于利用检索到的正常样本来引导异常图生成过程中的噪声抑制。RAID 从分层向量数据库中检索类级、语义级和实例级表示，形成由粗到细的流程。匹配代价体将输入与检索到的样例进行关联，随后由引导式混合专家（MoE）网络利用检索到的样本自适应地抑制匹配噪声并生成细粒度异常图。RAID 在 MVTec、VisA、MPDD 和 BTAD 基准上于全样本、少样本和多数据集设置下均取得最优性能。
英文原文摘要 1362 字符
Unsupervised Anomaly Detection (UAD) aims to identify abnormal regions by establishing correspondences between test images and normal templates. Existing methods primarily rely on image reconstruction or template retrieval but face a fundamental challenge: matching between test images and normal templates inevitably introduces noise due to intra-class variations, imperfect correspondences, and limited templates. Observing that Retrieval-Augmented Generation (RAG) leverages retrieved samples directly in the generation process, we reinterpret UAD through this lens and introduce RAID, a retrieval-augmented UAD framework designed for noise-resilient anomaly detection and localization. Unlike standard RAG that enriches context or knowledge, we focus on using retrieved normal samples to guide noise suppression in anomaly map generation. RAID retrieves class-, semantic-, and instance-level representations from a hierarchical vector database, forming a coarse-to-fine pipeline. A matching cost volume correlates the input with retrieved exemplars, followed by a guided Mixture-of-Experts (MoE) network that leverages the retrieved samples to adaptively suppress matching noise and produce fine-grained anomaly maps. RAID achieves state-of-the-art performance across full-shot, few-shot, and multi-dataset settings on MVTec, VisA, MPDD, and BTAD benchmarks.