RAID: Retrieval-Augmented Anomaly Detection
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 \textbf{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. \href{https://github.com/Mingxiu-Cai/RAID}{https://github.com/Mingxiu-Cai/RAID}.
Code (0)
등록된 구현이 없습니다.
Tasks
Unsupervised Anomaly DetectionImage ReconstructionSimilar Papers 제목 키워드 기반
RAIDX: A Retrieval-Augmented Generation and GRPO Reinforcement Learning Framework for Explainable Deepfake Detection
The rapid advancement of AI-generation models has enabled the creation of hyperrealistic imagery, posing ethical risks through widespread misinformation. Current deepfake detection methods, categorized as face specific d…
Reinforcement LearningDeepFake DetectionRetrieval Augmented Anomaly Detection (RAAD): Nimble Model Adjustment Without Retraining
We propose a novel mechanism for real-time (human-in-the-loop) feedback focused on false positive reduction to enhance anomaly detection models. It was designed for the lightweight deployment of a behavioral network anom…
Anomaly DetectionLightweight DeploymentRetrievalRetrieval-augmented GenerationAdaptable and Interpretable Framework for Novelty Detection in Real-Time IoT Systems
This paper presents the Real-time Adaptive and Interpretable Detection (RAID) algorithm. The novel approach addresses the limitations of state-of-the-art anomaly detection methods for multivariate dynamic processes, whic…
Anomaly DetectionNovelty DetectionRetrieval Augmented Deep Anomaly Detection for Tabular Data
Deep learning for tabular data has garnered increasing attention in recent years, yet employing deep models for structured data remains challenging. While these models excel with unstructured data, their efficacy with st…
Anomaly DetectionRetrievalEnhancing Retrieval in QA Systems with Derived Feature Association
Retrieval augmented generation (RAG) has become the standard in long context question answering (QA) systems. However, typical implementations of RAG rely on a rather naive retrieval mechanism, in which texts whose embed…
Question AnsweringRAGRetrievalRetrieval-augmented Generation