mlsanityData to 14 Oct 2026

Dual-Interrelated Diffusion Model for Few-Shot Anomaly Image Generation

arXiv 2408.13509 ↗First posted 24 Aug 2024cs.CVcited by 32

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

Abstract (arXiv)

The performance of anomaly inspection in industrial manufacturing is constrained by the scarcity of anomaly data. To overcome this challenge, researchers have started employing anomaly generation approaches to augment the anomaly dataset. However, existing anomaly generation methods suffer from limited diversity in the generated anomalies and struggle to achieve a seamless blending of this anomaly with the original image. Moreover, the generated mask is usually not aligned with the generated anomaly. In this paper, we overcome these challenges from a new perspective, simultaneously generating a pair of the overall image and the corresponding anomaly part. We propose DualAnoDiff, a novel diffusion-based few-shot anomaly image generation model, which can generate diverse and realistic anomaly images by using a dual-interrelated diffusion model, where one of them is employed to generate the whole image while the other one generates the anomaly part. Moreover, we extract background and shape information to mitigate the distortion and blurriness phenomenon in few-shot image generation. Extensive experiments demonstrate the superiority of our proposed model over state-of-the-art methods in terms of diversity, realism and the accuracy of mask. Overall, our approach significantly improves the performance of downstream anomaly inspection tasks, including anomaly detection, anomaly localization, and anomaly classification tasks.

Key facts. Cited by 32 papers in the map (data through 14 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 38 of its 53 references that are in the map. First posted on arXiv 24 Aug 2024.

Builds on

38 of 53 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Model10 Dec

Other references · 37

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  5. 2023Segment Anythingcited by 8,234
  6. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  7. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,300
  8. 2016Improved Techniques for Training GANscited by 2,970
  9. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,245
  10. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 776
  11. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 531
  12. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 514
25 more
  1. 2022Anomaly Detection via Reverse Distillation from One-Class Embeddingcited by 421
  2. 2020U2-Net: Going Deeper with Nested U-Structure for Salient Object Detectioncited by 412
  3. 2020Differentiable Augmentation for Data-Efficient GAN Trainingcited by 363
  4. 2023SimpleNet: A Simple Network for Image Anomaly Detection and Localizationcited by 256
  5. 2021Few-shot Image Generation via Cross-domain Correspondencecited by 207
  6. 2023Multimodal Industrial Anomaly Detection via Hybrid Fusioncited by 139
  7. 2024Real-IAD: A Real-World Multi-View Dataset for Benchmarking Versatile Industrial Anomaly Detectioncited by 139
  8. 2022CFA: Coupled-hypersphere-based Feature Adaptation for Target-Oriented Anomaly Localizationcited by 135
  9. 2020Freeze the Discriminator: a Simple Baseline for Fine-Tuning GANscited by 132
  10. 2021Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detectioncited by 119
  11. 2024Transparent Image Layer Diffusion using Latent Transparencycited by 114
  12. 2022Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detectioncited by 104
  13. 2021Defect-GAN: High-Fidelity Defect Synthesis for Automated Defect Inspectioncited by 77
  14. 2023Diffusion Model is Secretly a Training-free Open Vocabulary Semantic Segmentercited by 76
  15. 2021Explainable Deep Few-shot Anomaly Detection with Deviation Networkscited by 69
  16. 2023Few-Shot Defect Image Generation via Defect-Aware Feature Manipulationcited by 67
  17. 2022Prototypical Residual Networks for Anomaly Detection and Localizationcited by 56
  18. 2024MuSc: Zero-Shot Industrial Anomaly Classification and Segmentation with Mutual Scoring of the Unlabeled Imagescited by 52
  19. 2024Tuning-Free Image Customization with Image and Text Guidancecited by 25
  20. 2024Learning Unified Reference Representation for Unsupervised Multi-class Anomaly Detectioncited by 19
  21. 2024Continuous Memory Representation for Anomaly Detectioncited by 16
  22. 2022Few-shot Image Generation via Masked Discriminationcited by 12
  23. 2023Phasic Content Fusing Diffusion Model with Directional Distribution Consistency for Few-Shot Model Adaptioncited by 11
  24. 2022FRIH: Fine-grained Region-aware Image Harmonizationcited by 9
  25. 2024PSPU: Enhanced Positive and Unlabeled Learning by Leveraging Pseudo Supervisioncited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 13; 2026: 19.

32 papers.

Sort:

By area:

  1. 2025A Survey on Industrial Anomaly Synthesiscited by 7
  2. 2025Towards Fine-Grained Vision-Language Alignment for Few-Shot Anomaly Detectioncited by 4
  3. 2025Generate Aligned Anomaly: Region-Guided Few-Shot Anomaly Image-Mask Pair Synthesis for Industrial Inspectioncited by 3
  4. 2026MIRAGE: Model-agnostic Industrial Realistic Anomaly Generation and Evaluation for Visual Anomaly Detectioncited by 3
  5. 2026Latent Anomaly Knowledge Excavation: Unveiling Sparse Sensitive Neurons in Vision-Language Modelscited by 3
  6. 20253D-PNAS: 3D Industrial Surface Anomaly Synthesis with Perlin Noisecited by 2
  7. 2025A Comprehensive Survey for Real-World Industrial Defect Detection: Challenges, Approaches, and Prospectscited by 2
  8. 2025STAGE: Segmentation-oriented Industrial Anomaly Synthesis via Graded Diffusion with Explicit Mask Alignmentcited by 2
  9. 2025Universal Few-Shot Spatial Control for Diffusion Modelscited by 2
  10. 2026One-to-More: High-Fidelity Training-Free Anomaly Generation with Attention Controlcited by 2
  11. 2026IAD-Unify: Task-Specific Interfaces for Industrial Anomaly Understanding, Segmentation, and Generationcited by 2
  12. 2026Envisioning Beyond the Few: Disentangled Semantics and Primitives for Few-Shot Atypical Layout-to-Image Generationcited by 2
20 more
  1. 2025MAGIC: Few-Shot Mask-Guided Anomaly Inpainting with Prompt Perturbation, Spatially Adaptive Guidance, and Context Awarenesscited by 1
  2. 2025FaultDiffusion: Few-Shot Fault Time Series Generation with Diffusion Modelcited by 1
  3. 2025Anomaly Detection by Effectively Leveraging Synthetic Imagescited by 1
  4. 2025Double Helix Diffusion for Cross-Domain Anomaly Image Generationcited by 0
  5. 2025UniADC: A Unified Framework for Anomaly Detection and Classificationcited by 0
  6. 2025DeltaDeno: Zero-Shot Anomaly Generation via Delta-Denoising Attributioncited by 0
  7. 2026HLGFA: High-Low Resolution Guided Feature Alignment for Unsupervised Anomaly Detectioncited by 0
  8. 2026Semantic Iterative Reconstruction: One-Shot Universal Anomaly Detectioncited by 0
  9. 2026Synthesis4AD: Synthetic Anomalies are All You Need for 3D Anomaly Detectioncited by 0
  10. 2026GroundingAnomaly: Spatially-Grounded Diffusion for Few-Shot Anomaly Synthesiscited by 0
  11. 2026Large-Scale Universal Defect Generation: Foundation Models and Datasetscited by 0
  12. 2026Mixture Prototype Flow Matching for Open-Set Supervised Anomaly Detectioncited by 0
  13. 2026Anomaly-Preference Image Generationcited by 0
  14. 2026Point Cloud Diffusion with Global and Local Reconstruction for Instance-Level 3D Anomaly Detectioncited by 0
  15. 2026OSAGEN: Object-Aware Mask Priors and Multistage Decoupled Diffusion for Industrial Anomaly Generationcited by 0
  16. 2026UniScale: Arbitrary-Scale Industrial Anomaly Generationcited by 0
  17. 2026DeCo: Zero-Shot Industrial Anomaly Generation through Decoupling and Recouplingcited by 0
  18. 2026DPA: Decoupling Product-Agnostic Anomaly Representations for Zero-shot Anomaly Generationcited by 0
  19. 2026FLASH: A "Generate Once, Synthesize Many" Framework for Synthetic Anomaly Generation in Industrial Anomaly Detectioncited by 0
  20. 2026CORE: Contrast-and-Reflect for Self-Supervised Prompt Optimization in Anomaly Synthesiscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024AnomalySD: Few-Shot Multi-Class Anomaly Detection with Stable Diffusion Model
  2. 2025HDM: Hybrid Diffusion Model for Unified Image Anomaly Detection
  3. 2025Few-Shot Anomaly-Driven Generation for Anomaly Classification and Segmentation
  4. 2025Training-Free Anomaly Generation via Dual-Attention Enhancement in Diffusion Model
  5. 2023DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detection
  6. 2024Enhancing Multi-Class Anomaly Detection via Diffusion Refinement with Dual Conditioning
  7. 2025Correcting Deviations from Normality: A Reformulated Diffusion Model for Multi-Class Unsupervised Anomaly Detection
  8. 2024A Novel Approach to Industrial Defect Generation through Blended Latent Diffusion Model with Online Adaptation