mlsanityData to 7 Oct 2026

PyramidFlow: High-Resolution Defect Contrastive Localization using Pyramid Normalizing Flow

arXiv 2303.02595 ↗First posted 5 Mar 2023cs.CV cs.AIcited by 74

Not on the map. Why?

Abstract (arXiv)

During industrial processing, unforeseen defects may arise in products due to uncontrollable factors. Although unsupervised methods have been successful in defect localization, the usual use of pre-trained models results in low-resolution outputs, which damages visual performance. To address this issue, we propose PyramidFlow, the first fully normalizing flow method without pre-trained models that enables high-resolution defect localization. Specifically, we propose a latent template-based defect contrastive localization paradigm to reduce intra-class variance, as the pre-trained models do. In addition, PyramidFlow utilizes pyramid-like normalizing flows for multi-scale fusing and volume normalization to help generalization. Our comprehensive studies on MVTecAD demonstrate the proposed method outperforms the comparable algorithms that do not use external priors, even achieving state-of-the-art performance in more challenging BTAD scenarios.

Key facts. Cited by 74 papers in the map (data through 7 Oct 2026). Builds on 23 of its 32 references that are in the map. First posted on arXiv 5 Mar 2023.

Builds on

23 of 32 references.

References · 23

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2016Density estimation using Real NVPcited by 2,029
  3. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
  4. 2014NICE: Non-linear Independent Components Estimationcited by 1,052
  5. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 772
  6. 2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 591
  7. 2017Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoverycited by 566
  8. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 510
  9. 2019Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddingscited by 386
  10. 2021CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flowscited by 320
  11. 2020Sub-Image Anomaly Detection with Deep Pyramid Correspondencescited by 297
  12. 2018Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoderscited by 263
11 more
  1. 2021FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flowscited by 225
  2. 2021VT-ADL: A Vision Transformer Network for Image Anomaly Detection and Localizationcited by 222
  3. 2020Why Normalizing Flows Fail to Detect Out-of-Distribution Datacited by 220
  4. 2020Patch SVDD: Patch-level SVDD for Anomaly Detection and Segmentationcited by 212
  5. 2020Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flowscited by 212
  6. 2019Segmentation-Based Deep-Learning Approach for Surface-Defect Detectioncited by 145
  7. 2021Fully Convolutional Cross-Scale-Flows for Image-based Defect Detectioncited by 117
  8. 2021Mixed supervision for surface-defect detection: from weakly to fully supervised learningcited by 101
  9. 2022Anomalib: A Deep Learning Library for Anomaly Detectioncited by 75
  10. 2022Deep Learning for Unsupervised Anomaly Localization in Industrial Images: A Surveycited by 67
  11. 2018Deep Generative Model using Unregularized Score for Anomaly Detection with Heterogeneous Complexitycited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 9; 2024: 26; 2025: 24; 2026: 15.

74 papers.

Sort:

By area:

  1. 2023AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Modelscited by 169
  2. 2023Complementary Pseudo Multimodal Feature for Point Cloud Anomaly Detectioncited by 74
  3. 2024A Unified Anomaly Synthesis Strategy with Gradient Ascent for Industrial Anomaly Detection and Localizationcited by 74
  4. 2024MuSc: Zero-Shot Industrial Anomaly Classification and Segmentation with Mutual Scoring of the Unlabeled Imagescited by 52
  5. 2023Exploring Plain ViT Reconstruction for Multi-class Unsupervised Anomaly Detectioncited by 47
  6. 2025DriveLaW:Unifying Planning and Video Generation in a Latent Driving Worldcited by 43
  7. 2024Unsupervised Continual Anomaly Detection with Contrastively-learned Promptcited by 31
  8. 2023ReConPatch : Contrastive Patch Representation Learning for Industrial Anomaly Detectioncited by 30
  9. 2025AdaptCLIP: Adapting CLIP for Universal Visual Anomaly Detectioncited by 28
  10. 2024Towards High-resolution 3D Anomaly Detection via Group-Level Feature Contrastive Learningcited by 25
  11. 2024M3DM-NR: RGB-3D Noisy-Resistant Industrial Anomaly Detection via Multimodal Denoisingcited by 24
  12. 2023Target before Shooting: Accurate Anomaly Detection and Localization under One Millisecond via Cascade Patch Retrievalcited by 22
38 more
  1. 2024Learning Unified Reference Representation for Unsupervised Multi-class Anomaly Detectioncited by 19
  2. 2025Learning to Detect Multi-class Anomalies with Just One Normal Image Promptcited by 18
  3. 2024Learning Feature Inversion for Multi-class Anomaly Detection under General-purpose COCO-AD Benchmarkcited by 15
  4. 2024Is this Generated Person Existed in Real-world? Fine-grained Detecting and Calibrating Abnormal Human-bodycited by 12
  5. 2024AMI-Net: Adaptive Mask Inpainting Network for Industrial Anomaly Detection and Localizationcited by 12
  6. 2024Revisiting Multimodal Fusion for 3D Anomaly Detection from an Architectural Perspectivecited by 12
  7. 2025Real-IAD D3: A Real-World 2D/Pseudo-3D/3D Dataset for Industrial Anomaly Detectioncited by 12
  8. 2025MetaUAS: Universal Anomaly Segmentation with One-Prompt Meta-Learningcited by 12
  9. 2025Normal-Abnormal Guided Generalist Anomaly Detectioncited by 10
  10. 2024Learning Multi-view Anomaly Detection with Efficient Adaptive Selectioncited by 9
  11. 2024RAD: A Comprehensive Dataset for Benchmarking the Robustness of Image Anomaly Detectioncited by 8
  12. 2025Triad: Empowering LMM-based Anomaly Detection with Vision Expert-guided Visual Tokenizer and Manufacturing Processcited by 8
  13. 2025AD-FM: Multimodal LLMs for Anomaly Detection via Multi-Stage Reasoning and Fine-Grained Reward Optimizationcited by 8
  14. 2026InstaDrive: Instance-Aware Driving World Models for Realistic and Consistent Video Generationcited by 8
  15. 2024Dual-path Frequency Discriminators for Few-shot Anomaly Detectioncited by 7
  16. 2024Toward Multi-class Anomaly Detection: Exploring Class-aware Unified Model against Inter-class Interferencecited by 7
  17. 2024A Comprehensive Library for Benchmarking Multi-class Visual Anomaly Detectioncited by 7
  18. 2024ToCoAD: Two-Stage Contrastive Learning for Industrial Anomaly Detectioncited by 7
  19. 2025Center-aware Residual Anomaly Synthesis for Multi-class Industrial Anomaly Detectioncited by 7
  20. 2025Registration is a Powerful Rotation-Invariance Learner for 3D Anomaly Detectioncited by 7
  21. 2023Industrial Anomaly Detection and Localization Using Weakly-Supervised Residual Transformerscited by 6
  22. 2024Unsupervised Anomaly Detection via Masked Diffusion Posterior Samplingcited by 5
  23. 2025Multi-Flow: Multi-View-Enriched Normalizing Flows for Industrial Anomaly Detectioncited by 5
  24. 2024AUPIMO: Redefining Visual Anomaly Detection Benchmarks with High Speed and Low Tolerancecited by 4
  25. 2024Adapted-MoE: Mixture of Experts with Test-Time Adaption for Anomaly Detectioncited by 4
  26. 2026One Language-Free Foundation Model Is Enough for Universal Vision Anomaly Detectioncited by 4
  27. 2025FlexiClip: Locality-Preserving Free-Form Character Animationcited by 3
  28. 2025A Survey: Spatiotemporal Consistency in Video Generationcited by 3
  29. 2025Flow Along the K-Amplitude for Generative Modelingcited by 3
  30. 2025VLMDiff: Leveraging Vision-Language Models for Multi-Class Anomaly Detection with Diffusioncited by 3
  31. 2024A Recover-then-Discriminate Framework for Robust Anomaly Detectioncited by 2
  32. 2024Texture-AD: An Anomaly Detection Dataset and Benchmark for Real Algorithm Developmentcited by 2
  33. 2024FlowCLAS: Enhancing Normalizing Flow Via Contrastive Learning For Anomaly Segmentationcited by 2
  34. 2024Friend or Foe? Harnessing Controllable Overfitting for Anomaly Detectioncited by 2
  35. 2025BeltCrack: the First Sequential-image Industrial Conveyor Belt Crack Detection Dataset and Its Baseline with Triple-domain Feature Learningcited by 2
  36. 2025A Comprehensive Survey for Real-World Industrial Defect Detection: Challenges, Approaches, and Prospectscited by 2
  37. 2025BridgeNet: A Unified Multimodal Framework for Bridging 2D and 3D Industrial Anomaly Detectioncited by 2
  38. 2026ConsisDrive: Identity-Preserving Driving World Models for Video Generation by Instance Maskcited by 2

50 most cited of 74 All 74 (JSON)