GAN-based Defect Synthesis for Anomaly Detection in Fabrics
Abstract
Image-based quality control aims at detecting anomalies in products and is a crucial part of the production process. Challenges arise from the complexity and variety of products, defects, and the rarity of defect occurrence. Quality control thus still relies heavily on manual inspection. Supervised, data driven approaches have greatly improved performance, but suffer from a major drawback: They require large amounts of annotated training data, limiting their economic viability.In this work, we overcome this drawback by leveraging the consistency of defect appearance across fabrics to transfer knowledge about anomalies from one fabric to another. We realize this by adapting the image-to-image translation framework, introducing guidance by means of a segmentation map. We evaluate both image quality as well as usability of generated defects. For the image quality, both classical (L1, L2 and Structured Similarity Measurement (SSIM)) and perceptual (Learned Perceptual Image Patch Similarity (LPIPS)) metrics indicate efficacy of the presented approach, i.e. defect synthesis only occurs in the targeted regions, and the background fabric pattern remains largely unchanged. To evaluate usability of generated defects, we train pseudo-supervised models on synthesized defects of fabrics unseen during training. A comparison with semi-supervised, autoencoder based approaches demonstrates the suitability of our approach, yielding average Area Under the Receiver Operating Characteristic Curve (AUROC) values of 0.81 for pseudo-supervised vs. 0.69 for semi-supervised settings.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · see citing works
Unpaired image-to-image translation using cycle-consistent adversarial networks
Zhu, J.-Y., Park, T., Isola, P., & Efros, A. A. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.244 · Cited by 23,602 · see citing works
Image-to-Image Translation with Conditional Adversarial Networks
Isola, P., Zhu, J.-Y., Zhou, T., & Efros, A. A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.632 · Cited by 22,930 · see citing works
Labaca-Castro, R. (2023) · Springer eBooks · doi:10.1007/978-3-658-40442-0_9 · Cited by 21,100 · see citing works
GAN（Generative Adversarial Nets）
淳司, 柴. (2017) · Journal of Japan Society for Fuzzy Theory and Intelligent Informatics · doi:10.3156/jsoft.29.5_177_2 · Cited by 19,268 · see citing works
The Unreasonable Effectiveness of Deep Features as a Perceptual Metric
Zhang, R., Isola, P., Efros, A. A., Shechtman, E., & Wang, O. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00068 · Cited by 14,623 · see citing works
Chandola, V., Banerjee, A., & Kumar, V. (2009) · ACM Computing Surveys · doi:10.1145/1541880.1541882 · Cited by 11,687 · see citing works
GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., & Hochreiter, S. (2017) · arXiv · doi:10.48550/arxiv.1706.08500 · Cited by 8,365 · see citing works
Improved Techniques for Training GANs
Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., & Chen, X. (2016) · arXiv · doi:10.48550/arxiv.1606.03498 · Cited by 6,965 · see citing works
Image Style Transfer Using Convolutional Neural Networks
Gatys, L. A., Ecker, A. S., & Bethge, M. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.265 · Cited by 6,025 · see citing works
“Least squares generative adversarial networks,”
Mao, X., Li, Q., Xie, H., Lau, R. Y. K., Wang, Z., & Smolley, S. P. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.304 · Cited by 5,437 · see citing works
Arbitrary Style Transfer in Real-Time with Adaptive Instance Normalization
Huang, X., & Belongie, S. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.167 · Cited by 5,076 · see citing works
Instance Normalization: The Missing Ingredient for Fast StylizationPreprint
Ulyanov, D., Vedaldi, A., & Lempitsky, V. (2016) · arXiv.org · doi:10.48550/arxiv.1607.08022 · Cited by 4,239 · see citing works
Spectral Normalization for Generative Adversarial Networks
Miyato, T., Kataoka, T., Koyama, M., & Yoshida, Y. (2018) · arXiv · doi:10.48550/arxiv.1802.05957 · Cited by 3,438 · see citing works
On the Variance of the Adaptive Learning Rate and BeyondPreprint
Liu, L., Jiang, H., He, P., Chen, W., Liu, X., Gao, J., & Han, J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.03265 · Cited by 1,529 · see citing works
The Perception-Distortion Tradeoff
Blau, Y., & Michaeli, T. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00652 · Cited by 1,001 · see citing works
Texture Synthesis Using Convolutional Neural NetworksPreprint
Gatys, L. A., Ecker, A. S., & Bethge, M. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1505.07376 · Cited by 902 · see citing works
Unsupervised Cross-Domain Image GenerationPreprint
Taigman, Y., Polyak, A., & Wolf, L. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.02200 · Cited by 901 · see citing works
Automated fabric defect detection—A review
Ngan, H. Y. T., Pang, G. K. H., & Yung, N. H. C. (2011) · Image and Vision Computing · doi:10.1016/j.imavis.2011.02.002 · Cited by 550 · see citing works
Universal Style Transfer via Feature TransformsPreprint
Li, Y., Chen, F., Yang, J., Wang, Z., Lü, X., & Yang, M. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1705.08086 · Cited by 538 · see citing works
Controlling Perceptual Factors in Neural Style Transfer
Gatys, L. A., Ecker, A. S., Bethge, M., Hertzmann, A., & Shechtman, E. (2017) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2017.397 · Cited by 495 · see citing works
Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired DataPreprint
Almahairi, A., Rajeswar, S., Sordoni, A., Bachman, P., & Courville, A. C. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1802.10151 · Cited by 356 · see citing works
Universal Style Transfer via Feature Transforms
Li, Y., Chen, F., Yan, S., Wang, Z., Lü, X., & Yang, M. (2017) · neural information processing systems · Cited by 300 · see citing works
Mei, S., Wang, Y., & Wen, G. (2018) · Sensors · doi:10.3390/s18041064 · Cited by 284 · see citing works
(1999) · The MIT Press eBooks · doi:10.7551/mitpress/7011.001.0001 · Cited by 271 · see citing works
Unsupervised learning : foundations of neural computation
Hinton, G. E., & Sejnowski, T. J. (1999) · Cited by 270 · see citing works
Fabric defect detection systems and methods—A systematic literature review
Hanbay, K., Talu, M. F., & Özgüven, Ö. F. (2016) · Optik · doi:10.1016/j.ijleo.2016.09.110 · Cited by 268 · see citing works
Attention-GAN for Object Transfiguration in Wild Images
Chen, X., Xu, C., Yang, X., & Tao, D. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01216-8_11 · Cited by 188 · see citing works
Unsupervised fabric defect detection based on a deep convolutional generative adversarial network
Hu, G., Huang, J., Wang, Q., Li, J., Xu, Z., & Huang, X. (2019) · Textile Research Journal · doi:10.1177/0040517519862880 · Cited by 172 · see citing works
FDAS: A Knowledge-based Framework for Analysis of Defects in Woven Textile Structures
Srinivasan, K., Dastoor, P. H., Radhakrishnaiah, P., & Jayaraman, S. (1992) · Journal of the Textile Institute · doi:10.1080/00405009208631217 · Cited by 138 · see citing works
Yarn-dyed Fabric Defect Detection with YOLOV2 Based on Deep Convolution Neural Networks
Zhang, H., Zhang, L., Li, P., & Gu, D. (2018) · IEEE Data Driven Control and Learning Systems Conference (DDCLS) · doi:10.1109/ddcls.2018.8516094 · Cited by 85 · see citing works
Karayiannis, Y., Stojanovic, R. D., Mitropoulos, P., Koulamas, C., Stouraitis, T., Koubias, S., & Papadopoulos, G. T. (2003) · IEEE International Conference on Electronics, Circuits and Systems (ICECS) · doi:10.1109/icecs.1999.813221 · Cited by 63 · see citing works
Fabric Defect Detection Based on Faster RCNN
Wei, B., Hao, K., Tang, X., & Ren, L. (2018) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-99695-0_6 · Cited by 62 · see citing works
Autoencoder-Based Fabric Defect Detection with Cross- Patch Similarity
Tian, H., & Li, F. (2019) · doi:10.23919/mva.2019.8758051 · Cited by 30 · see citing works
Woven Fabric Defect Detection Based on Convolutional Neural Network for Binary Classification
Gao, C., Zhou, J., Wong, W. K., & Gao, T. (2018) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-99695-0_37 · Cited by 18 · see citing works
Patterned Fabric Defect Detection and Classification (FDDC) Techniques: A Review
Oni, D. I., Ojo, J. A., Alabi, B. O., Adebayo, A. A., & Amoran, A. E. (2018) · International Journal of Scientific and Engineering Research · doi:10.14299/ijser.2018.02.002 · Cited by 10 · see citing works
Flagged first, then by citations
4 of the 40 references couldn’t be matched to a known paper.
Cited by
Sorted by citations
Deep Industrial Image Anomaly Detection: A Survey
Liu, J., Xie, G., Wang, J., Li, S., Wang, C., Zheng, F., & Jin, Y. (2024) · Machine Intelligence Research · doi:10.1007/s11633-023-1459-z · Cited by 463 · see citing works
“[155] use CycleGAN [156] containing ResNet/U-Net as a generator as the basic architecture to transfer defects from one fabric to another.”
Deep Learning for Unsupervised Anomaly Localization in Industrial Images: A Survey
Tao, X., Gong, X., Zhang, X., Yan, S., & Adak, C. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3196436 · Cited by 228 · see citing works
“Some works, e.g., [75] and [76], applied CycleGAN to rail defect detection and fiber anomalies inspection.”
An Overview of Image Generation of Industrial Surface Defects
Zhong, X., Zhu, J., Liu, W., Hu, C., Deng, Y., & Wu, Z. (2023) · Sensors · doi:10.3390/s23198160 · Cited by 41 · see citing works
“[63] 2020 Improvement of segmented mapping-based structures on CycleGAN with introduction of least squares error and spectral normalisation You can specify where defects are generated without using pairs of data The colour consistency of the generated defect images could be improved”
MethodGenerative AI in industrial machine vision: a review
Zhou, H. A., Wolfschläger, D., Florides, C., Werheid, J., Behnen, H., Woltersmann, J.-H., PINTO, T. L. F. D. C., Kemmerling, M., Abdelrazeq, A., & Schmitt, R. H. (2025) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-025-02604-6 · Cited by 62 · see citing works
A Review on the Influence of Deep Learning and Generative AI in the Fashion Industry
Imtiaz, A., Pathirana, N., Saheel, S., Karunanayaka, K. T., & Trenado, C. (2024) · Journal of Future Artificial Intelligence and Technologies · doi:10.62411/faith.3048-3719-29 · Cited by 18 · see citing works
“Similarly, [37] trained a GAN model on individual defect types in an image-to-image translation framework requiring a limited annotated training dataset and synthesized defects into new fabrics at the locations specified by a segmentation mask of arbitrary shape.”
MethodThe role of machine vision in industry 4.0: A textile manufacturing perspective
Konstantinidis, F. K., Kansizoglou, I., Tsintotas, K. A., Mouroutsos, S. G., & Gasteratos, A. C. (2021) · IEEE International Conference on Imaging Systems and Techniques (IST) · doi:10.1109/ist50367.2021.9651459 · Cited by 18 · see citing works
ul-Huda, N., Ahmad, H., Banjar, A., Alzahrani, A. O., Ahmad, I., & Naeem, M. S. (2024) · Heliyon · doi:10.1016/j.heliyon.2024.e26466 · Cited by 14 · see citing works
“Fabric defects are a significant issue that can affect product quality, customer satisfaction, and overall profitability [2].”
BackgroundIndustrial and medical anomaly detection through cycle-consistent adversarial networks
Bougaham, A., Delchevalerie, V., Adoui, M. E., & Frénay, B. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.128762 · Cited by 10 · see citing works
Anomaly Detection for Automated Visual Inspection: A Review
Rippel, O., & Merhof, D. (2023) · Technologien für die intelligente Automation · doi:10.1007/978-3-662-66769-9_1 · Cited by 6 · see citing works
Self-citationIncreasing the Generalization of Supervised Fabric Anomaly Detection Methods to Unseen Fabrics
Rippel, O., Zwinge, C., & Merhof, D. (2022) · Sensors · doi:10.3390/s22134750 · Cited by 6 · see citing works
“As a remedy for the poor performance of supervised models on unseen fabrics, generative adversarial networks (GANs) are commonly employed to synthesize defects/anomalies in the unseen fabrics.”
BackgroundInfluentialSelf-citationXie, X., Li, C., Qing, R., Zhou, C., & Zhang, Z. (2024) · Digital Signal Processing · doi:10.1016/j.dsp.2024.104441 · Cited by 5 · see citing works
MST: Multiscale Flow-Based Student–Teacher Network for Unsupervised Anomaly Detection
Yang, Y., Yang, Y., Zhou, S., Gao, Y., Zhu, Y., Wan, X., Hu, W., & Jiang, X. (2024) · Electronics · doi:10.3390/electronics13163224 · Cited by 4 · see citing works
Comparison of unsupervised image anomaly detection models for sheet metal glue lines
Chen, S., Bandaru, S., Marti, S., Bekar, E. T., & Skoogh, A. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.110740 · Cited by 4 · see citing works
Anomaly Detection for the Automated Visual Inspection of PET Preform Closures
Rippel, O., Haumering, P., Brauers, J., & Merhof, D. (2021) · IEEE International Conference on Emerging Technologies and Factory Automation (ETFA) · doi:10.1109/etfa45728.2021.9613298 · Cited by 4 · see citing works
Self-citationFeng, Z., Li, C., Ma, J., Wang, Z., Xiao, L., & Jiang, R. (2025) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-025-02666-6 · Cited by 3 · see citing works
“Researchers (Liu et al., 2019; Rippel et al., 2020 ; Niu et al., 2020; Wei et al., 2020 ) have utilized Generative Adversarial Networks to generate defective images based on a large set of defect-free images.”
Adversarial Defect Synthesis for Industrial Products in Low Data Regime
Coscia, P., Genovese, A., Scotti, F., & Piuri, V. (2023) · Proceedings - International Conference on Image Processing · doi:10.1109/icip49359.2023.10222874 · Cited by 1 · see citing works
“[14] define a semantic-aware approach that employs a translation model to improve an anomaly detection classifier with pseudo-images representing synthetic defective samples.”
BackgroundGeneration of Synthetic Image Anomalies for Analysis
Breuss, D., Rusý, K., Götzinger, M., & Jantsch, A. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-82150-9_2 · Cited by 1 · see citing works
Wang, S., Hu, Y., Liu, X., Wang, S., Wang, G., Xu, C., Liu, J., & Chen, P. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3675432 · Cited by 1 · see citing works
“By contrast, [37] ignores the abundance of anomalies in the cross-domain.”
Tseng, S., & Tsai, Y.-K. (2024) · International Journal of Pattern Recognition and Artificial Intelligence · doi:10.1142/s0218001424500198
Rahman, S. I. A., Tista, S. C., & Hoq, M. N. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-97-7426-5_3
Li, F., Li, D., Huang, L., Chen, H., & Zhang, M. (2025) · Asia Conference on Algorithms, Computing and Machine Learning (CACML) · doi:10.1109/cacml64929.2025.11010951
“Rippel et al. [8] use CycleGAN [9] to transfer defects.”
Semi-supervised deep learning for robust anomaly detection in smart manufacturing systems
Le, T. (2024) · theses.fr (ABES) · doi:10.70675/19d23228zf030z4df7za3abz596d36577818
- Authors
- Rippel, O., Muller, M., & Merhof, D.
- Affiliations
- RWTH Aachen University (DE)
- Venue
- 2020 25th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA)
- Publisher
- IEEE
- Published
- 2020-09
- Pages
- 534-540
- OpenAlex
- W3092105412
- Cited by
- 22
- References
- 40
- Citations by year
- 2026: 1 · 2025: 6 · 2024: 8 · 2023: 3 · 2022: 2 · 2021: 2
- FWCI
- 2.49
- Type
- conference paper
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE International Conference on Emerging Technologies and Factory Automation (ETFA) (publishedVersion)
- RWTH Publications (RWTH Aachen) (submittedVersion)
- Topics
- Physical Sciences › Engineering › Industrial and Manufacturing Engineering › Industrial Vision Systems and Defect Detection
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis
- Physical Sciences › Engineering › Civil and Structural Engineering › Infrastructure Maintenance and Monitoring
- Keywords
- anomaly detection, textiles, generative adversarial networks, image-to-image translation, domain adaptation, semi-supervised learning, image quality assessment, quality control
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
