mlsanityData to 14 Oct 2026

Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flows

arXiv 2008.12577 ↗First posted 28 Aug 2020cs.CV cs.LG eess.IVcited by 212

Not on the map. Why?

Abstract (arXiv)

The detection of manufacturing errors is crucial in fabrication processes to ensure product quality and safety standards. Since many defects occur very rarely and their characteristics are mostly unknown a priori, their detection is still an open research question. To this end, we propose DifferNet: It leverages the descriptiveness of features extracted by convolutional neural networks to estimate their density using normalizing flows. Normalizing flows are well-suited to deal with low dimensional data distributions. However, they struggle with the high dimensionality of images. Therefore, we employ a multi-scale feature extractor which enables the normalizing flow to assign meaningful likelihoods to the images. Based on these likelihoods we develop a scoring function that indicates defects. Moreover, propagating the score back to the image enables pixel-wise localization. To achieve a high robustness and performance we exploit multiple transformations in training and evaluation. In contrast to most other methods, ours does not require a large number of training samples and performs well with as low as 16 images. We demonstrate the superior performance over existing approaches on the challenging and newly proposed MVTec AD and Magnetic Tile Defects datasets.

Key facts. Cited by 212 papers in the map (data through 14 Oct 2026). First posted on arXiv 28 Aug 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 18; 2022: 35; 2023: 49; 2024: 51; 2025: 36; 2026: 23.

212 papers.

Sort:

By area:

  1. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 776
  2. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 531
  3. 2021CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flowscited by 321
  4. 2023WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentationcited by 315
  5. 2023SimpleNet: A Simple Network for Image Anomaly Detection and Localizationcited by 256
  6. 2021FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flowscited by 227
  7. 2023EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latenciescited by 160
  8. 2023SE(3)-Stochastic Flow Matching for Protein Backbone Generationcited by 150
  9. 2023Deep Industrial Image Anomaly Detection: A Surveycited by 148
  10. 2023Multimodal Industrial Anomaly Detection via Hybrid Fusioncited by 139
  11. 2022CFA: Coupled-hypersphere-based Feature Adaptation for Target-Oriented Anomaly Localizationcited by 135
  12. 2022Registration based Few-Shot Anomaly Detectioncited by 133
38 more
  1. 2021Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detectioncited by 119
  2. 2021Fully Convolutional Cross-Scale-Flows for Image-based Defect Detectioncited by 117
  3. 2022Asymmetric Student-Teacher Networks for Industrial Anomaly Detectioncited by 117
  4. 2024MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detectioncited by 113
  5. 2024PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detectioncited by 98
  6. 2021Inpainting Transformer for Anomaly Detectioncited by 91
  7. 2021Probabilistic Monocular 3D Human Pose Estimation with Normalizing Flowscited by 85
  8. 2023BMAD: Benchmarks for Medical Anomaly Detectioncited by 82
  9. 2022Omni-frequency Channel-selection Representations for Unsupervised Anomaly Detectioncited by 80
  10. 2023PyramidFlow: High-Resolution Defect Contrastive Localization using Pyramid Normalizing Flowcited by 74
  11. 2022Explicit Boundary Guided Semi-Push-Pull Contrastive Learning for Supervised Anomaly Detectioncited by 72
  12. 2022Deep Learning for Unsupervised Anomaly Localization in Industrial Images: A Surveycited by 68
  13. 2023IM-IAD: Industrial Image Anomaly Detection Benchmark in Manufacturingcited by 64
  14. 2021A Hierarchical Transformation-Discriminating Generative Model for Few Shot Anomaly Detectioncited by 60
  15. 2023Collaborative Discrepancy Optimization for Reliable Image Anomaly Localizationcited by 57
  16. 2022Prototypical Residual Networks for Anomaly Detection and Localizationcited by 56
  17. 2023Anomaly Detection with Conditioned Denoising Diffusion Modelscited by 56
  18. 2024SoftPatch: Unsupervised Anomaly Detection with Noisy Datacited by 55
  19. 2023Exploring Plain ViT Reconstruction for Multi-class Unsupervised Anomaly Detectioncited by 47
  20. 2023DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detectioncited by 46
  21. 2023PAD: A Dataset and Benchmark for Pose-agnostic Anomaly Detectioncited by 46
  22. 2024R3D-AD: Reconstruction via Diffusion for 3D Anomaly Detectioncited by 45
  23. 2023EasyNet: An Easy Network for 3D Industrial Anomaly Detectioncited by 43
  24. 2023Multimodal Industrial Anomaly Detection by Crossmodal Feature Mappingcited by 42
  25. 2022Self-Supervised Masked Convolutional Transformer Block for Anomaly Detectioncited by 34
  26. 2022Non-isotropy Regularization for Proxy-based Deep Metric Learningcited by 33
  27. 2023Cheating Depth: Enhancing 3D Surface Anomaly Detection via Depth Simulationcited by 33
  28. 2023Focus the Discrepancy: Intra- and Inter-Correlation Learning for Image Anomaly Detectioncited by 32
  29. 2024Unsupervised Continual Anomaly Detection with Contrastively-learned Promptcited by 31
  30. 2022MAEDAY: MAE for few and zero shot AnomalY-Detectioncited by 30
  31. 2023ReConPatch : Contrastive Patch Representation Learning for Industrial Anomaly Detectioncited by 30
  32. 2024PO3AD: Predicting Point Offsets toward Better 3D Point Cloud Anomaly Detectioncited by 30
  33. 2024Hierarchical Gaussian Mixture Normalizing Flow Modeling for Unified Anomaly Detectioncited by 28
  34. 2024MedIAnomaly: A comparative study of anomaly detection in medical imagescited by 26
  35. 2024PPFlow: Target-aware Peptide Design with Torsional Flow Matchingcited by 26
  36. 2023MSFlow: Multi-Scale Flow-based Framework for Unsupervised Anomaly Detectioncited by 25
  37. 2024SplatPose & Detect: Pose-Agnostic 3D Anomaly Detectioncited by 25
  38. 2024Towards High-resolution 3D Anomaly Detection via Group-Level Feature Contrastive Learningcited by 25

50 most cited of 212 All 212 (JSON)