mlsanityData to 7 Oct 2026

DiAD: A Diffusion-based Framework for Multi-class Anomaly Detection

arXiv 2312.06607 ↗First posted 11 Dec 2023cs.CVcited by 33

On the map: Diffusion models → Flow matching, time series and science

Abstract (arXiv)

Reconstruction-based approaches have achieved remarkable outcomes in anomaly detection. The exceptional image reconstruction capabilities of recently popular diffusion models have sparked research efforts to utilize them for enhanced reconstruction of anomalous images. Nonetheless, these methods might face challenges related to the preservation of image categories and pixel-wise structural integrity in the more practical multi-class setting. To solve the above problems, we propose a Difusion-based Anomaly Detection (DiAD) framework for multi-class anomaly detection, which consists of a pixel-space autoencoder, a latent-space Semantic-Guided (SG) network with a connection to the stable diffusion's denoising network, and a feature-space pre-trained feature extractor. Firstly, The SG network is proposed for reconstructing anomalous regions while preserving the original image's semantic information. Secondly, we introduce Spatial-aware Feature Fusion (SFF) block to maximize reconstruction accuracy when dealing with extensively reconstructed areas. Thirdly, the input and reconstructed images are processed by a pre-trained feature extractor to generate anomaly maps based on features extracted at different scales. Experiments on MVTec-AD and VisA datasets demonstrate the effectiveness of our approach which surpasses the state-of-the-art methods, e.g., achieving 96.8/52.6 and 97.2/99.0 (AUROC/AP) for localization and detection respectively on multi-class MVTec-AD dataset. Code will be available at https://lewandofskee.github.io/projects/diad.

Key facts. Cited by 33 papers in the map (data through 7 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 43 of its 59 references that are in the map. First posted on arXiv 11 Dec 2023.

Builds on

43 of 59 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Anomaly Detection with Conditioned Denoising Diffusion Models25 May

Other references · 42

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  5. 2020Denoising Diffusion Implicit Modelscited by 9,655
  6. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  7. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  8. 2016Wide Residual Networkscited by 3,057
  9. 2022Imagen Video: High Definition Video Generation with Diffusion Modelscited by 1,765
  10. 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,187
  11. 2017Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learningcited by 935
  12. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 772
30 more
  1. 2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 591
  2. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 529
  3. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 510
  4. 2021The RSNA-ASNR-MICCAI BraTS 2021 Benchmark on Brain Tumor Segmentation and Radiogenomic Classificationcited by 507
  5. 2019The Liver Tumor Segmentation Benchmark (LiTS)cited by 504
  6. 2022Anomaly Detection via Reverse Distillation from One-Class Embeddingcited by 419
  7. 2022DiffusionDet: Diffusion Model for Object Detectioncited by 354
  8. 2021CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flowscited by 320
  9. 2020Multiresolution Knowledge Distillation for Anomaly Detectioncited by 285
  10. 2022A Unified Model for Multi-class Anomaly Detectioncited by 267
  11. 2021FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flowscited by 225
  12. 2020Patch SVDD: Patch-level SVDD for Anomaly Detection and Segmentationcited by 212
  13. 2023Deep Industrial Image Anomaly Detection: A Surveycited by 147
  14. 2023Multimodal Industrial Anomaly Detection via Hybrid Fusioncited by 138
  15. 2022Registration based Few-Shot Anomaly Detectioncited by 133
  16. 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
  17. 2020Explainable Deep One-Class Classificationcited by 126
  18. 2022Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detectioncited by 104
  19. 2023BMAD: Benchmarks for Medical Anomaly Detectioncited by 81
  20. 2023Pushing the Limits of Fewshot Anomaly Detection in Industry Vision: Graphcorecited by 75
  21. 2022Deep Learning for Unsupervised Anomaly Localization in Industrial Images: A Surveycited by 67
  22. 2023Segment Any Anomaly without Training via Hybrid Prompt Regularizationcited by 59
  23. 2023CLIP-AD: A Language-Guided Staged Dual-Path Model for Zero-shot Anomaly Detectioncited by 58
  24. 2023EasyNet: An Easy Network for 3D Industrial Anomaly Detectioncited by 43
  25. 2022EATFormer: Improving Vision Transformer Inspired by Evolutionary Algorithmcited by 27
  26. 2023GPT-4V-AD: Exploring Grounding Potential of VQA-oriented GPT-4V for Zero-shot Anomaly Detectioncited by 23
  27. 2020TrustMAE: A Noise-Resilient Defect Classification Framework using Memory-Augmented Auto-Encoders with Trust Regionscited by 21
  28. 2021Reconstruction Student with Attention for Student-Teacher Pyramid Matchingcited by 20
  29. 2022Reconstruction from edge image combined with color and gradient difference for industrial surface anomaly detectioncited by 18
  30. 2023PVG: Progressive Vision Graph for Vision Recognitioncited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 16; 2025: 13; 2026: 3.

33 papers.

Sort:

By area:

  1. 2024AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detectioncited by 126
  2. 2024Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detectioncited by 92
  3. 2025AA-CLIP: Enhancing Zero-shot Anomaly Detection via Anomaly-Aware CLIPcited by 72
  4. 2024A Survey on Visual Anomaly Detection: Challenge, Approach, and Prospectcited by 69
  5. 2023Exploring Plain ViT Reconstruction for Multi-class Unsupervised Anomaly Detectioncited by 47
  6. 2024GLAD: Towards Better Reconstruction with Global and Local Adaptive Diffusion Models for Unsupervised Anomaly Detectioncited by 42
  7. 2024M3DM-NR: RGB-3D Noisy-Resistant Industrial Anomaly Detection via Multimodal Denoisingcited by 24
  8. 2024Prior Normality Prompt Transformer for Multi-class Industrial Image Anomaly Detectioncited by 19
  9. 2025Anomaly Detection and Generation with Diffusion Models: A Surveycited by 8
  10. 2024Dual-path Frequency Discriminators for Few-shot Anomaly Detectioncited by 7
  11. 2025Towards Accurate Unified Anomaly Segmentationcited by 7
  12. 2025One-to-Normal: Anomaly Personalization for Few-shot Anomaly Detectioncited by 7
21 more
  1. 2025FastRef:Fast Prototype Refinement for Few-Shot Industrial Anomaly Detectioncited by 6
  2. 2024DMAD: Dual Memory Bank for Real-World Anomaly Detectioncited by 5
  3. 2024VQ-Flow: Taming Normalizing Flows for Multi-Class Anomaly Detection via Hierarchical Vector Quantizationcited by 5
  4. 2024ROADS: Robust Prompt-driven Multi-Class Anomaly Detection under Domain Shiftcited by 5
  5. 2025UniMMAD: Unified Multi-Modal and Multi-Class Anomaly Detection via MoE-Driven Feature Decompressioncited by 3
  6. 2024MiniMaxAD: A Lightweight Autoencoder for Feature-Rich Anomaly Detectioncited by 2
  7. 2024Enhancing Multi-Class Anomaly Detection via Diffusion Refinement with Dual Conditioningcited by 2
  8. 2024Friend or Foe? Harnessing Controllable Overfitting for Anomaly Detectioncited by 2
  9. 2025PA-CLIP: Enhancing Zero-Shot Anomaly Detection through Pseudo-Anomaly Awarenesscited by 2
  10. 2025ResAD++: Towards Class Agnostic Anomaly Detection via Residual Feature Learningcited by 2
  11. 2024Anomaly Detection by Adapting a pre-trained Vision Language Modelcited by 1
  12. 2024A Study on Unsupervised Anomaly Detection and Defect Localization using Generative Model in Ultrasonic Non-Destructive Testingcited by 1
  13. 2025IQE-CLIP: Instance-aware Query Embedding for Zero-/Few-shot Anomaly Detection in Medical Domaincited by 1
  14. 2025ADPretrain: Advancing Industrial Anomaly Detection via Anomaly Representation Pretrainingcited by 1
  15. 2026HAAF: Hierarchical Adaptation and Alignment of Foundation Models for Few-Shot Pathology Anomaly Detectioncited by 1
  16. 2026MMR-AD: A Large-Scale Multimodal Dataset for Benchmarking General Anomaly Detection with Multimodal Large Language Modelscited by 1
  17. 2024CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIPcited by 0
  18. 2025Bi-Grid Reconstruction for Image Anomaly Detectioncited by 0
  19. 2025SP-Mamba: Spatial-Perception State Space Model for Unsupervised Medical Anomaly Detectioncited by 0
  20. 2025MIRAD - A comprehensive real-world robust anomaly detection dataset for Mass Individualizationcited by 0
  21. 2026Industrial Surface Defect Detection via Diffusion Generation and Asymmetric Student-Teacher Networkcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Correcting Deviations from Normality: A Reformulated Diffusion Model for Multi-Class Unsupervised Anomaly Detection
  2. 2023DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detection
  3. 2025InvAD: Inversion-based Reconstruction-Free Anomaly Detection with Diffusion Models
  4. 2026Dual Prototype-Conditioned Diffusion Model for Scalable Multi-Class Unsupervised Anomaly Detection in Large Category Spaces
  5. 2024Anomaly detection using Diffusion-based methods
  6. 2023TransFusion -- A Transparency-Based Diffusion Model for Anomaly Detection
  7. 2025HDM: Hybrid Diffusion Model for Unified Image Anomaly Detection
  8. 2025Single-Step Reconstruction-Free Anomaly Detection and Segmentation via Diffusion Models