mlsanityData to 7 Oct 2026

Defect-GAN: High-Fidelity Defect Synthesis for Automated Defect Inspection

arXiv 2103.15158 ↗First posted 28 Mar 2021cs.CVcited by 77

Not on the map. Why?

Abstract (arXiv)

Automated defect inspection is critical for effective and efficient maintenance, repair, and operations in advanced manufacturing. On the other hand, automated defect inspection is often constrained by the lack of defect samples, especially when we adopt deep neural networks for this task. This paper presents Defect-GAN, an automated defect synthesis network that generates realistic and diverse defect samples for training accurate and robust defect inspection networks. Defect-GAN learns through defacement and restoration processes, where the defacement generates defects on normal surface images while the restoration removes defects to generate normal images. It employs a novel compositional layer-based architecture for generating realistic defects within various image backgrounds with different textures and appearances. It can also mimic the stochastic variations of defects and offer flexible control over the locations and categories of the generated defects within the image background. Extensive experiments show that Defect-GAN is capable of synthesizing various defects with superior diversity and fidelity. In addition, the synthesized defect samples demonstrate their effectiveness in training better defect inspection networks.

Key facts. Cited by 77 papers in the map (data through 7 Oct 2026). Builds on 51 of its 75 references that are in the map. First posted on arXiv 28 Mar 2021.

Builds on

51 of 75 references.

References · 51

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2016Densely Connected Convolutional Networkscited by 6,691
  5. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  6. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  7. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  8. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  9. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  10. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  11. 2017Improved Training of Wasserstein GANscited by 2,223
  12. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
38 more
  1. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  2. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  3. 2016Context Encoders: Feature Learning by Inpaintingcited by 1,424
  4. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,295
  5. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  6. 2019StarGAN v2: Diverse Image Synthesis for Multiple Domainscited by 1,095
  7. 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,036
  8. 2018Multimodal Unsupervised Image-to-Image Translationcited by 795
  9. 2019A Closer Look at Few-shot Classificationcited by 679
  10. 2017Unsupervised Image-to-Image Translation Networkscited by 602
  11. 2018Generative Image Inpainting with Contextual Attentioncited by 578
  12. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
  13. 2018Dynamic Few-Shot Visual Learning without Forgettingcited by 385
  14. 2020Differentiable Augmentation for Data-Efficient GAN Trainingcited by 361
  15. 2020Frustratingly Simple Few-Shot Object Detectioncited by 280
  16. 2017Learning to Discover Cross-Domain Relations with Generative Adversarial Networkscited by 278
  17. 2017Data Augmentation Generative Adversarial Networkscited by 278
  18. 2018Few-shot Object Detection via Feature Reweightingcited by 265
  19. 2019Few-Shot Object Detection with Attention-RPN and Multi-Relation Detectorcited by 206
  20. 2019Meta R-CNN : Towards General Solver for Instance-level Few-shot Learningcited by 182
  21. 2018Low-Shot Learning from Imaginary Datacited by 181
  22. 2016EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesiscited by 177
  23. 2019f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learningcited by 164
  24. 2018GANimation: Anatomically-aware Facial Animation from a Single Imagecited by 160
  25. 2016Semantic Image Inpainting with Deep Generative Modelscited by 156
  26. 2019Seeing What a GAN Cannot Generatecited by 148
  27. 2018Shift-Net: Image Inpainting via Deep Feature Rearrangementcited by 87
  28. 2018Spatial Fusion GAN for Image Synthesiscited by 68
  29. 2018Unsupervised Attention-guided Image to Image Translationcited by 58
  30. 2018FineGAN: Unsupervised Hierarchical Disentanglement for Fine-Grained Object Generation and Discoverycited by 58
  31. 2020Semantically Multi-modal Image Synthesiscited by 58
  32. 2018Verisimilar Image Synthesis for Accurate Detection and Recognition of Texts in Scenescited by 44
  33. 2021Meta-DETR: Image-Level Few-Shot Object Detection with Inter-Class Correlation Exploitationcited by 44
  34. 2019CAD-Net: A Context-Aware Detection Network for Objects in Remote Sensing Imagerycited by 43
  35. 2020Cascade EF-GAN: Progressive Facial Expression Editing with Local Focusescited by 43
  36. 2017LR-GAN: Layered Recursive Generative Adversarial Networks for Image Generationcited by 36
  37. 2019Meta-learning Convolutional Neural Architectures for Multi-target Concrete Defect Classification with the COncrete DEfect BRidge IMage Datasetcited by 21
  38. 2019How to make a pizza: Learning a compositional layer-based GAN modelcited by 21

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 3; 2023: 12; 2024: 17; 2025: 28; 2026: 13.

77 papers.

Sort:

By area:

  1. 2023Deep Industrial Image Anomaly Detection: A Surveycited by 147
  2. 2023AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Modelcited by 110
  3. 2021Diverse Image Inpainting with Bidirectional and Autoregressive Transformerscited by 80
  4. 2023Few-Shot Defect Image Generation via Defect-Aware Feature Manipulationcited by 66
  5. 2023Exploring Plain ViT Reconstruction for Multi-class Unsupervised Anomaly Detectioncited by 47
  6. 2021Unbalanced Feature Transport for Exemplar-based Image Translationcited by 41
  7. 2024Facing the Elephant in the Room: Visual Prompt Tuning or Full Finetuning?cited by 31
  8. 2024Dual-Interrelated Diffusion Model for Few-Shot Anomaly Image Generationcited by 31
  9. 2024SeaS: Few-shot Industrial Anomaly Image Generation with Separation and Sharing Fine-tuningcited by 26
  10. 2024M3DM-NR: RGB-3D Noisy-Resistant Industrial Anomaly Detection via Multimodal Denoisingcited by 24
  11. 2024Unseen Visual Anomaly Generationcited by 23
  12. 2024AnomalyXFusion: Multi-modal Anomaly Synthesis with Diffusioncited by 21
38 more
  1. 2023Defect Spectrum: A Granular Look of Large-Scale Defect Datasets with Rich Semanticscited by 16
  2. 2024Learning Feature Inversion for Multi-class Anomaly Detection under General-purpose COCO-AD Benchmarkcited by 15
  3. 2021GenCo: Generative Co-training for Generative Adversarial Networks with Limited Datacited by 14
  4. 2024Long-Tailed Anomaly Detection with Learnable Class Namescited by 14
  5. 2025DefectFill: Realistic Defect Generation with Inpainting Diffusion Model for Visual Inspectioncited by 12
  6. 2023Defect Transfer GAN: Diverse Defect Synthesis for Data Augmentationcited by 9
  7. 2024Few-shot Defect Image Generation based on Consistency Modelingcited by 8
  8. 2025Anomaly Detection and Generation with Diffusion Models: A Surveycited by 8
  9. 2022Semantic-Aligned Matching for Enhanced DETR Convergence and Multi-Scale Feature Fusioncited by 7
  10. 2024A Comprehensive Library for Benchmarking Multi-class Visual Anomaly Detectioncited by 7
  11. 2024AnomalyControl: Learning Cross-modal Semantic Features for Controllable Anomaly Synthesiscited by 7
  12. 2025Towards Accurate Unified Anomaly Segmentationcited by 7
  13. 2025A Survey on Industrial Anomaly Synthesiscited by 7
  14. 2023Industrial Anomaly Detection and Localization Using Weakly-Supervised Residual Transformerscited by 6
  15. 2024A Novel Approach to Industrial Defect Generation through Blended Latent Diffusion Model with Online Adaptationcited by 6
  16. 2024A Comprehensive Survey on Machine Learning Driven Material Defect Detectioncited by 5
  17. 2025AnomalyPainter: Vision-Language-Diffusion Synergy for Zero-Shot Realistic and Diverse Industrial Anomaly Synthesiscited by 5
  18. 2025Multi-Flow: Multi-View-Enriched Normalizing Flows for Industrial Anomaly Detectioncited by 5
  19. 2023Improving the Effectiveness of Deep Generative Datacited by 4
  20. 2024Defect Image Sample Generation With Diffusion Prior for Steel Surface Defect Recognitioncited by 4
  21. 2025Exploring Few-Shot Defect Segmentation in General Industrial Scenarios with Metric Learning and Vision Foundation Modelscited by 4
  22. 2025Component-aware Unsupervised Logical Anomaly Generation for Industrial Anomaly Detectioncited by 4
  23. 2025AnoStyler: Text-Driven Localized Anomaly Generation via Lightweight Style Transfercited by 4
  24. 2024Synth4Seg -- Learning Defect Data Synthesis for Defect Segmentation using Bi-level Optimizationcited by 3
  25. 2025"Stones from Other Hills can Polish Jade": Zero-shot Anomaly Image Synthesis via Cross-domain Anomaly Injectioncited by 3
  26. 2021FBC-GAN: Diverse and Flexible Image Synthesis via Foreground-Background Compositioncited by 2
  27. 2022Synthetic Defect Generation for Display Front-of-Screen Quality Inspection: A Surveycited by 2
  28. 2023Industrial and Medical Anomaly Detection Through Cycle-Consistent Adversarial Networkscited by 2
  29. 2024SYNOSIS: Image synthesis pipeline for machine vision in metal surface inspectioncited by 2
  30. 20253D-PNAS: 3D Industrial Surface Anomaly Synthesis with Perlin Noisecited by 2
  31. 2025Generate Aligned Anomaly: Region-Guided Few-Shot Anomaly Image-Mask Pair Synthesis for Industrial Inspectioncited by 2
  32. 2025STAGE: Segmentation-oriented Industrial Anomaly Synthesis via Graded Diffusion with Explicit Mask Alignmentcited by 2
  33. 2026AnomalyVFM -- Transforming Vision Foundation Models into Zero-Shot Anomaly Detectorscited by 2
  34. 2022Repainting and Imitating Learning for Lane Detectioncited by 1
  35. 2023Generative Model-Driven Synthetic Training Image Generation: An Approach to Cognition in Rail Defect Detectioncited by 1
  36. 2024AnomalyFactory: Regard Anomaly Generation as Unsupervised Anomaly Localizationcited by 1
  37. 2025AnomalyHybrid: A Domain-agnostic Generative Framework for General Anomaly Detectioncited by 1
  38. 2025MAGIC: Few-Shot Mask-Guided Anomaly Inpainting with Prompt Perturbation, Spatially Adaptive Guidance, and Context Awarenesscited by 1

50 most cited of 77 All 77 (JSON)