mlsanityData to 7 Oct 2026

A Unified Anomaly Synthesis Strategy with Gradient Ascent for Industrial Anomaly Detection and Localization

arXiv 2407.09359 ↗First posted 12 Jul 2024cs.CVcited by 74

Not on the map. Why?

Abstract (arXiv)

Anomaly synthesis strategies can effectively enhance unsupervised anomaly detection. However, existing strategies have limitations in the coverage and controllability of anomaly synthesis, particularly for weak defects that are very similar to normal regions. In this paper, we propose Global and Local Anomaly co-Synthesis Strategy (GLASS), a novel unified framework designed to synthesize a broader coverage of anomalies under the manifold and hypersphere distribution constraints of Global Anomaly Synthesis (GAS) at the feature level and Local Anomaly Synthesis (LAS) at the image level. Our method synthesizes near-in-distribution anomalies in a controllable way using Gaussian noise guided by gradient ascent and truncated projection. GLASS achieves state-of-the-art results on the MVTec AD (detection AUROC of 99.9%), VisA, and MPDD datasets and excels in weak defect detection. The effectiveness and efficiency have been further validated in industrial applications for woven fabric defect detection. The code and dataset are available at: urlhttps://github.com/cqylunlun/GLASS.

Key facts. Cited by 74 papers in the map (data through 7 Oct 2026). Builds on 32 of its 42 references that are in the map. First posted on arXiv 12 Jul 2024.

Builds on

32 of 42 references.

References · 32

  1. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,261
  2. 2013Describing Textures in the Wildcited by 2,110
  3. 2016Density estimation using Real NVPcited by 2,029
  4. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 772
  5. 2016Training Region-based Object Detectors with Online Hard Example Miningcited by 577
  6. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 529
  7. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 510
  8. 2022Anomaly Detection via Reverse Distillation from One-Class Embeddingcited by 419
  9. 2018GANomaly: Semi-Supervised Anomaly Detection via Adversarial Trainingcited by 409
  10. 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 397
  11. 2021CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flowscited by 320
  12. 2020Multiresolution Knowledge Distillation for Anomaly Detectioncited by 285
20 more
  1. 2022A Unified Model for Multi-class Anomaly Detectioncited by 267
  2. 2023SimpleNet: A Simple Network for Image Anomaly Detection and Localizationcited by 256
  3. 2021FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flowscited by 225
  4. 2020PANDA: Adapting Pretrained Features for Anomaly Detection and Segmentationcited by 175
  5. 2023EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latenciescited by 157
  6. 2022DeSTSeg: Segmentation Guided Denoising Student-Teacher for Anomaly Detectioncited by 153
  7. 2023Deep Industrial Image Anomaly Detection: A Surveycited by 147
  8. 2022CFA: Coupled-hypersphere-based Feature Adaptation for Target-Oriented Anomaly Localizationcited by 135
  9. 2020DROCC: Deep Robust One-Class Classificationcited by 121
  10. 2021Natural Synthetic Anomalies for Self-Supervised Anomaly Detection and Localizationcited by 116
  11. 2022DSR -- A dual subspace re-projection network for surface anomaly detectioncited by 89
  12. 2021Divide-and-Assemble: Learning Block-wise Memory for Unsupervised Anomaly Detectioncited by 83
  13. 2023PyramidFlow: High-Resolution Defect Contrastive Localization using Pyramid Normalizing Flowcited by 74
  14. 2022Explicit Boundary Guided Semi-Push-Pull Contrastive Learning for Supervised Anomaly Detectioncited by 72
  15. 2022PNI : Industrial Anomaly Detection using Position and Neighborhood Informationcited by 69
  16. 2022MemSeg: A semi-supervised method for image surface defect detection using differences and commonalitiescited by 68
  17. 2022Rethinking Reconstruction Autoencoder-Based Out-of-Distribution Detectioncited by 59
  18. 2023Collaborative Discrepancy Optimization for Reliable Image Anomaly Localizationcited by 56
  19. 2023ReConPatch : Contrastive Patch Representation Learning for Industrial Anomaly Detectioncited by 30
  20. 2023Restricted Generative Projection for One-Class Classification and Anomaly Detectioncited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 5; 2025: 39; 2026: 30.

74 papers.

Sort:

By area:

  1. 2025Towards Zero-Shot Anomaly Detection and Reasoning with Multimodal Large Language Modelscited by 54
  2. 2024SeaS: Few-shot Industrial Anomaly Image Generation with Separation and Sharing Fine-tuningcited by 26
  3. 2025One-for-More: Continual Diffusion Model for Anomaly Detectioncited by 19
  4. 2024Progressive Boundary Guided Anomaly Synthesis for Industrial Anomaly Detectioncited by 16
  5. 2024VMAD: Visual-enhanced Multimodal Large Language Model for Zero-Shot Anomaly Detectioncited by 13
  6. 2025Triad: Empowering LMM-based Anomaly Detection with Vision Expert-guided Visual Tokenizer and Manufacturing Processcited by 8
  7. 2025PatchGuard: Adversarially Robust Anomaly Detection and Localization through Vision Transformers and Pseudo Anomaliescited by 8
  8. 2025A Survey on Industrial Anomaly Synthesiscited by 7
  9. 2025Center-aware Residual Anomaly Synthesis for Multi-class Industrial Anomaly Detectioncited by 7
  10. 2025INP-Former++: Advancing Universal Anomaly Detection via Intrinsic Normal Prototypes and Residual Learningcited by 7
  11. 2025Dinomaly2: A Unified Framework for Unsupervised Image Anomaly Detectioncited by 6
  12. 2025A Survey on Foundation-Model-Based Industrial Defect Detectioncited by 5
38 more
  1. 2025CostFilter-AD: Enhancing Anomaly Detection through Matching Cost Filteringcited by 5
  2. 2025Kaputt: A Large-Scale Dataset for Visual Defect Detectioncited by 5
  3. 2026MRAD: Zero-Shot Anomaly Detection with Memory-Driven Retrievalcited by 5
  4. 2025Continual-MEGA: A Large-scale Benchmark for Generalizable Continual Anomaly Detectioncited by 4
  5. 2025"Stones from Other Hills can Polish Jade": Zero-shot Anomaly Image Synthesis via Cross-domain Anomaly Injectioncited by 3
  6. 2025Crane: Context-Guided Prompt Learning and Attention Refinement for Zero-Shot Anomaly Detectioncited by 3
  7. 2025Visual Anomaly Detection under Complex View-Illumination Interplay: A Large-Scale Benchmarkcited by 3
  8. 2025RoBiS: Robust Binary Segmentation for High-Resolution Industrial Imagescited by 3
  9. 2025Towards Fine-Grained Vision-Language Alignment for Few-Shot Anomaly Detectioncited by 3
  10. 2025MuSc-V2: Zero-Shot Multimodal Industrial Anomaly Classification and Segmentation with Mutual Scoring of Unlabeled Samplescited by 3
  11. 2024Friend or Foe? Harnessing Controllable Overfitting for Anomaly Detectioncited by 2
  12. 2025ISP-AD: A Large-Scale Real-World Dataset for Advancing Industrial Anomaly Detection with Synthetic and Real Defectscited by 2
  13. 2025A Comprehensive Survey for Real-World Industrial Defect Detection: Challenges, Approaches, and Prospectscited by 2
  14. 2025STAGE: Segmentation-oriented Industrial Anomaly Synthesis via Graded Diffusion with Explicit Mask Alignmentcited by 2
  15. 2026MIRAGE: Model-agnostic Industrial Realistic Anomaly Generation and Evaluation for Visual Anomaly Detectioncited by 2
  16. 2026TinyGLASS: Real-Time Self-Supervised In-Sensor Anomaly Detectioncited by 2
  17. 2026A Principled Approach to Unsupervised Anomaly Detectioncited by 2
  18. 2025Masked Autoencoder Self Pre-Training for Defect Detection in Microelectronicscited by 1
  19. 2025Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Conceptscited by 1
  20. 2025CoPS: Conditional Prompt Synthesis for Zero-Shot Anomaly Detectioncited by 1
  21. 2025A Contrastive Learning-Guided Confident Meta-learning for Zero Shot Anomaly Detectioncited by 1
  22. 2025Resilient Multimodal Industrial Surface Defect Detection with Uncertain Sensors Availabilitycited by 1
  23. 2025From Benchmarks to Reality: Advancing Visual Anomaly Detection by the VAND 3.0 Challengecited by 1
  24. 2025ADPretrain: Advancing Industrial Anomaly Detection via Anomaly Representation Pretrainingcited by 1
  25. 2026MMR-AD: A Large-Scale Multimodal Dataset for Benchmarking General Anomaly Detection with Multimodal Large Language Modelscited by 1
  26. 2026OPD-IAD: From Language Judgment to Industrial Anomaly Detection via On-Policy Self-Distillationcited by 1
  27. 2024LADMIM: Logical Anomaly Detection with Masked Image Modeling in Discrete Latent Spacecited by 0
  28. 2025Beyond Academic Benchmarks: Critical Analysis and Best Practices for Visual Industrial Anomaly Detectioncited by 0
  29. 2025PathoSCOPE: Few-Shot Pathology Detection via Self-Supervised Contrastive Learning and Pathology-Informed Synthetic Embeddingscited by 0
  30. 2025From Lab to Factory: Pitfalls and Guidelines for Self-/Unsupervised Defect Detection on Low-Quality Industrial Imagescited by 0
  31. 2025Bridge Feature Matching and Cross-Modal Alignment with Mutual-filtering for Zero-shot Anomaly Detectioncited by 0
  32. 2025SARD: Segmentation-Aware Anomaly Synthesis via Region-Constrained Diffusion with Discriminative Mask Guidancecited by 0
  33. 2025FAST: Foreground-aware Diffusion with Accelerated Sampling Trajectory for Segmentation-oriented Anomaly Synthesiscited by 0
  34. 2025UniADC: A Unified Framework for Anomaly Detection and Classificationcited by 0
  35. 2025Noise & pattern: identity-anchored Tikhonov regularization for robust structural anomaly detectioncited by 0
  36. 2025DeltaDeno: Zero-Shot Anomaly Generation via Delta-Denoising Attributioncited by 0
  37. 20253D Human-Human Interaction Anomaly Detectioncited by 0
  38. 2025Towards Pixel-Wise Anomaly Location for High-Resolution PCBA via Self-Supervised Image Reconstructioncited by 0

50 most cited of 74 All 74 (JSON)