mlsanityData to 7 Oct 2026

RAID: Retrieval-Augmented Anomaly Detection

arXiv 2602.19611 ↗First posted 23 Feb 2026cs.CVcited by 2

On the map: Retrieval-augmented generation → Privacy and security of RAG

Abstract (arXiv)

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. hrefhttps://github.com/Mingxiu-Cai/RAIDhttps://github.com/Mingxiu-Cai/RAID.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Privacy and security of RAG, one of 15 directions in Retrieval-augmented generation. Builds on 53 of its 75 references that are in the map. First posted on arXiv 23 Feb 2026.

Builds on

53 of 75 references.

References · 53

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  4. 2023Segment Anythingcited by 8,158
  5. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  6. 2025Qwen2.5-VL Technical Reportcited by 5,418
  7. 2021Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsitycited by 3,014
  8. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  9. 2025DINOv3cited by 1,297
  10. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 772
  11. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 510
  12. 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 397
38 more
  1. 2023WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentationcited by 311
  2. 2023AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detectioncited by 270
  3. 2022A Unified Model for Multi-class Anomaly Detectioncited by 267
  4. 2023SimpleNet: A Simple Network for Image Anomaly Detection and Localizationcited by 256
  5. 2021VT-ADL: A Vision Transformer Network for Image Anomaly Detection and Localizationcited by 222
  6. 2022Re-Imagen: Retrieval-Augmented Text-to-Image Generatorcited by 208
  7. 2023APRIL-GAN: A Zero-/Few-Shot Anomaly Classification and Segmentation Method for CVPR 2023 VAND Workshop Challenge Tracks 1&2: 1st Place on Zero-shot AD and 4th Place on Few-shot ADcited by 128
  8. 2024AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detectioncited by 126
  9. 2024MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detectioncited by 113
  10. 2022Retrieval Augmented Classification for Long-Tail Visual Recognitioncited by 106
  11. 2024Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detectioncited by 92
  12. 2021Divide-and-Assemble: Learning Block-wise Memory for Unsupervised Anomaly Detectioncited by 83
  13. 2024A Survey on Visual Anomaly Detection: Challenge, Approach, and Prospectcited by 69
  14. 2024Adapting Visual-Language Models for Generalizable Anomaly Detection in Medical Imagescited by 69
  15. 2023Hierarchical Vector Quantized Transformer for Multi-class Unsupervised Anomaly Detectioncited by 66
  16. 2024RAGChecker: A Fine-grained Framework for Diagnosing Retrieval-Augmented Generationcited by 59
  17. 2025VDocRAG: Retrieval-Augmented Generation over Visually-Rich Documentscited by 57
  18. 2024AnomalyDINO: Boosting Patch-based Few-shot Anomaly Detection with DINOv2cited by 53
  19. 2024Text Prompt with Normality Guidance for Weakly Supervised Video Anomaly Detectioncited by 49
  20. 2023Exploring Plain ViT Reconstruction for Multi-class Unsupervised Anomaly Detectioncited by 47
  21. 2023DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detectioncited by 46
  22. 2023TransFusion -- A Transparency-Based Diffusion Model for Anomaly Detectioncited by 43
  23. 2024GLAD: Towards Better Reconstruction with Global and Local Adaptive Diffusion Models for Unsupervised Anomaly Detectioncited by 42
  24. 2023Diversity-Measurable Anomaly Detectioncited by 41
  25. 2025Retrieval Augmented Generation and Understanding in Vision: A Survey and New Outlookcited by 32
  26. 2024SeaS: Few-shot Industrial Anomaly Image Generation with Separation and Sharing Fine-tuningcited by 26
  27. 2023MSFlow: Multi-Scale Flow-based Framework for Unsupervised Anomaly Detectioncited by 25
  28. 2024Retrieval-Augmented Open-Vocabulary Object Detectioncited by 20
  29. 2024Retrieval-augmented Few-shot Medical Image Segmentation with Foundation Modelscited by 20
  30. 2025Learning to Detect Multi-class Anomalies with Just One Normal Image Promptcited by 18
  31. 2024ReFIR: Grounding Large Restoration Models with Retrieval Augmentationcited by 15
  32. 2025Retrieval-Augmented Dynamic Prompt Tuning for Incomplete Multimodal Learningcited by 15
  33. 2025MRAMG-Bench: A Comprehensive Benchmark for Advancing Multimodal Retrieval-Augmented Multimodal Generationcited by 15
  34. 2025DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookupcited by 9
  35. 2024Cross-Modal Learning for Anomaly Detection in Complex Industrial Process: Methodology and Benchmarkcited by 8
  36. 2025PatchGuard: Adversarially Robust Anomaly Detection and Localization through Vision Transformers and Pseudo Anomaliescited by 8
  37. 2025Foundation Models and Transformers for Anomaly Detection: A Surveycited by 8
  38. 2025Towards Real Unsupervised Anomaly Detection Via Confident Meta-Learningcited by 8

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026HiMatch-AD: DINOv3-driven Hierarchical Matching for Training-free Medical Anomaly Detectioncited by 0
  2. 2026UniVAD v2: Unified Visual Anomaly Detection via Support-Conditioned Boundary Constructioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Retrieval Augmented Anomaly Detection (RAAD): Nimble Model Adjustment Without Retraining
  2. 2025ADNet: A Large-Scale and Extensible Multi-Domain Benchmark for Anomaly Detection Across 380 Real-World Categories
  3. 2023Generating and Reweighting Dense Contrastive Patterns for Unsupervised Anomaly Detection
  4. 2025One-to-Normal: Anomaly Personalization for Few-shot Anomaly Detection
  5. 2026Keep the Needle, Prune the Haystack: Defect-Preserving Token Pruning for Efficient Zero-Shot Anomaly Detection
  6. 2025UniMMAD: Unified Multi-Modal and Multi-Class Anomaly Detection via MoE-Driven Feature Decompression
  7. 2024Unseen Visual Anomaly Generation
  8. 2024Adapted-MoE: Mixture of Experts with Test-Time Adaption for Anomaly Detection