mlsanityData to 7 Oct 2026

Unseen Visual Anomaly Generation

arXiv 2406.01078 ↗First posted 3 Jun 2024cs.CVcited by 23

Not on the map. Why?

Abstract (arXiv)

Visual anomaly detection (AD) presents significant challenges due to the scarcity of anomalous data samples. While numerous works have been proposed to synthesize anomalous samples, these synthetic anomalies often lack authenticity or require extensive training data, limiting their applicability in real-world scenarios. In this work, we propose Anomaly Anything (AnomalyAny), a novel framework that leverages Stable Diffusion (SD)'s image generation capabilities to generate diverse and realistic unseen anomalies. By conditioning on a single normal sample during test time, AnomalyAny is able to generate unseen anomalies for arbitrary object types with text descriptions. Within AnomalyAny, we propose attention-guided anomaly optimization to direct SD attention on generating hard anomaly concepts. Additionally, we introduce prompt-guided anomaly refinement, incorporating detailed descriptions to further improve the generation quality. Extensive experiments on MVTec AD and VisA datasets demonstrate AnomalyAny's ability in generating high-quality unseen anomalies and its effectiveness in enhancing downstream AD performance.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). Builds on 29 of its 34 references that are in the map. First posted on arXiv 3 Jun 2024.

Builds on

29 of 34 references.

References · 29

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2023GPT-4 Technical Reportcited by 18,132
  5. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  6. 2013Describing Textures in the Wildcited by 2,110
  7. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 772
  8. 2023Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Modelscited by 696
  9. 2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 591
  10. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 529
  11. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 510
  12. 2022Anomaly Detection via Reverse Distillation from One-Class Embeddingcited by 419
17 more
  1. 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 397
  2. 2023WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentationcited by 311
  3. 2022A Unified Model for Multi-class Anomaly Detectioncited by 267
  4. 2021Few-shot Image Generation via Cross-domain Correspondencecited by 206
  5. 2023AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Modelscited by 169
  6. 2021Natural Synthetic Anomalies for Self-Supervised Anomaly Detection and Localizationcited by 116
  7. 2024RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detectioncited by 116
  8. 2023AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Modelcited by 110
  9. 2024PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detectioncited by 97
  10. 2021Defect-GAN: High-Fidelity Defect Synthesis for Automated Defect Inspectioncited by 77
  11. 2024A Survey on Visual Anomaly Detection: Challenge, Approach, and Prospectcited by 69
  12. 2023Few-Shot Defect Image Generation via Defect-Aware Feature Manipulationcited by 66
  13. 2023Hierarchical Vector Quantized Transformer for Multi-class Unsupervised Anomaly Detectioncited by 66
  14. 2023Collaborative Discrepancy Optimization for Reliable Image Anomaly Localizationcited by 56
  15. 2024AnomalyXFusion: Multi-modal Anomaly Synthesis with Diffusioncited by 21
  16. 2023Defect Spectrum: A Granular Look of Large-Scale Defect Datasets with Rich Semanticscited by 16
  17. 2023NNG-Mix: Improving Semi-supervised Anomaly Detection with Pseudo-anomaly Generationcited by 14

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 10; 2026: 13.

23 papers.

Sort:

By area:

  1. 2025A Survey on Industrial Anomaly Synthesiscited by 7
  2. 2025"Stones from Other Hills can Polish Jade": Zero-shot Anomaly Image Synthesis via Cross-domain Anomaly Injectioncited by 3
  3. 2025Towards Fine-Grained Vision-Language Alignment for Few-Shot Anomaly Detectioncited by 3
  4. 2025ISP-AD: A Large-Scale Real-World Dataset for Advancing Industrial Anomaly Detection with Synthetic and Real Defectscited by 2
  5. 2025Real-IAD Variety: Pushing Industrial Anomaly Detection Dataset to a Modern Eracited by 2
  6. 2026GCR: Geometry-Consistent Routing for Task-Agnostic Continual Anomaly Detectioncited by 2
  7. 2026MIRAGE: Model-agnostic Industrial Realistic Anomaly Generation and Evaluation for Visual Anomaly Detectioncited by 2
  8. 2025Anomaly Detection by Effectively Leveraging Synthetic Imagescited by 1
  9. 2026Adaptive Confidence Regularization for Multimodal Failure Detectioncited by 1
  10. 2026One-to-More: High-Fidelity Training-Free Anomaly Generation with Attention Controlcited by 1
  11. 2025UniADC: A Unified Framework for Anomaly Detection and Classificationcited by 0
  12. 2025DeltaDeno: Zero-Shot Anomaly Generation via Delta-Denoising Attributioncited by 0
11 more
  1. 2025Explainable Visual Anomaly Detection via Concept Bottleneck Modelscited by 0
  2. 2025DRL-Guided Neural Batch Sampling for Semi-Supervised Pixel-Level Anomaly Detectioncited by 0
  3. 2026Multimodal Learning for Arcing Detection in Pantograph-Catenary Systemscited by 0
  4. 2026Novel Anomaly Detection Scenarios and Evaluation Metrics to Address the Ambiguity in the Definition of Normal Samplescited by 0
  5. 2026Mixture Prototype Flow Matching for Open-Set Supervised Anomaly Detectioncited by 0
  6. 2026Anomaly-Preference Image Generationcited by 0
  7. 2026T2S: A Rehearsal-Based Approach for Extraction-Resistant Model Watermarkingcited by 0
  8. 2026DeCo: Zero-Shot Industrial Anomaly Generation through Decoupling and Recouplingcited by 0
  9. 2026DPA: Decoupling Product-Agnostic Anomaly Representations for Zero-shot Anomaly Generationcited by 0
  10. 2026Supervision Recovery for Time Series Anomaly Detection via Context-Anchored Pairingcited by 0
  11. 2026Visual Anomaly Synthesis for Model Selection in Data Scarcitycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Training-Free Anomaly Generation via Dual-Attention Enhancement in Diffusion Model
  2. 2025Few-Shot Anomaly-Driven Generation for Anomaly Classification and Segmentation
  3. 2025One-to-Normal: Anomaly Personalization for Few-shot Anomaly Detection
  4. 2024AnomalySD: Few-Shot Multi-Class Anomaly Detection with Stable Diffusion Model
  5. 2026AnomalyVFM -- Transforming Vision Foundation Models into Zero-Shot Anomaly Detectors
  6. 2024AnomalyDINO: Boosting Patch-based Few-shot Anomaly Detection with DINOv2
  7. 2025From Benchmarks to Reality: Advancing Visual Anomaly Detection by the VAND 3.0 Challenge
  8. 2025Anomagic: Crossmodal Prompt-driven Zero-shot Anomaly Generation