{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T12:52:24Z","timestamp":1781614344215,"version":"3.54.5"},"reference-count":40,"publisher":"MDPI AG","issue":"10","license":[{"start":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T00:00:00Z","timestamp":1760572800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>In industrial settings, defect detection using deep learning typically requires large numbers of defective samples. However, defective products are rare on production lines, creating a scarcity of defect samples and an overabundance of samples that contain only background. We introduce ImbDef-GAN, a sample imbalance generative framework, to address three persistent limitations in defect image generation: unnatural transitions at defect background boundaries, misalignment between defects and their masks, and out-of-bounds defect placement. The framework operates in two stages: (i) background image generation and (ii) defect image generation conditioned on the generated background. In the background image-generation stage, a lightweight StyleGAN3 variant jointly generates the background image and its segmentation mask. A Progress-coupled Gated Detail Injection module uses global scheduling driven by training progress and per-pixel gating to inject high-frequency information in a controlled manner, thereby enhancing background detail while preserving training stability. In the defect image-generation stage, the design augments the background generator with a residual branch that extracts defect features. By blending defect features with a smoothing coefficient, the resulting defect boundaries transition more naturally and gradually. A mask-aware matching discriminator enforces consistency between each defect image and its mask. In addition, an Edge Structure Loss and a Region Consistency Loss strengthen morphological fidelity and spatial constraints within the valid mask region. Extensive experiments on the MVTec AD dataset demonstrate that ImbDef-GAN surpasses existing methods in both the realism and diversity of generated defects. When the generated data are used to train a downstream detector, YOLOv11 achieves a 5.4% improvement in mAP@0.5, indicating that the proposed approach effectively improves detection accuracy under sample imbalance.<\/jats:p>","DOI":"10.3390\/jimaging11100367","type":"journal-article","created":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T16:33:22Z","timestamp":1760632402000},"page":"367","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["ImbDef-GAN: Defect Image-Generation Method Based on Sample Imbalance"],"prefix":"10.3390","volume":"11","author":[{"given":"Dengbiao","family":"Jiang","sequence":"first","affiliation":[{"name":"School of Computer Science, Jiangsu University of Science and Technology, Zhenjiang 212003, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nian","family":"Tao","sequence":"additional","affiliation":[{"name":"School of Computer Science, Jiangsu University of Science and Technology, Zhenjiang 212003, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kelong","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Jiangsu University of Science and Technology, Zhenjiang 212003, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiming","family":"Wang","sequence":"additional","affiliation":[{"name":"Tofflon Science & Technology Group Co., Ltd., Shanghai 200000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5360-0788","authenticated-orcid":false,"given":"Haijian","family":"Shao","sequence":"additional","affiliation":[{"name":"School of Computer Science, Jiangsu University of Science and Technology, Zhenjiang 212003, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,10,16]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3439950","article-title":"Deep learning for anomaly detection: A review","volume":"54","author":"Pang","year":"2021","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"5592878","DOI":"10.1155\/2021\/5592878","article-title":"A new steel defect detection algorithm based on deep learning","volume":"2021","author":"Zhao","year":"2021","journal-title":"Comput. Intell. Neurosci."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"112776","DOI":"10.1016\/j.measurement.2023.112776","article-title":"RDD-YOLO: A modified YOLO for detection of steel surface defects","volume":"214","author":"Zhao","year":"2023","journal-title":"Measurement"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Guo, Z., Wang, C., Yang, G., Huang, Z., and Li, G. (2022). Msft-YOLO: Improved YOLOv5 based on transformer for detecting defects of steel surface. Sensors, 22.","DOI":"10.3390\/s22093467"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016, January 27\u201330). You only look once: Unified, real-time object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref_6","unstructured":"Ren, S., He, K., Girshick, R., and Sun, J. (2015, January 7\u201312). Faster R-CNN: Towards real-time object detection with region proposal networks. Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), Montreal, QC, Canada."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Zavrtanik, V., Kristan, M., and Sko\u010daj, D. (2022, January 23\u201327). DSR\u2014A dual subspace re-projection network for surface anomaly detection. Proceedings of the European Conference on Computer Vision (ECCV), Tel Aviv, Israel.","DOI":"10.1007\/978-3-031-19821-2_31"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Bergmann, P., Fauser, M., Sattlegger, D., and Steger, C. (2020, January 14\u201319). Uninformed students: Student-teacher anomaly detection with discriminative latent embeddings. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00424"},{"key":"ref_9","unstructured":"DeVries, T., and Taylor, G.W. (2017). Improved regularization of convolutional neural networks with cutout. arXiv."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Li, C.-L., Sohn, K., Yoon, J., and Pfister, T. (2021, January 20\u201325). CutPaste: Self-supervised learning for anomaly detection and localization. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.00954"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Lin, D., Cao, Y., Zhu, W., and Li, Y. (2020). Few-shot defect segmentation leveraging abundant defect free training samples through normal background regularization and crop-and-paste operation. arXiv.","DOI":"10.1109\/ICME51207.2021.9428468"},{"key":"ref_12","unstructured":"Ho, J., Jain, A., and Abbeel, P. (2020, January 6\u201312). Denoising diffusion probabilistic models. Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), Virtual Conference."},{"key":"ref_13","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (2014, January 8\u201313). Generative adversarial nets. Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), Montreal, QC, Canada."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Zhu, J.-Y., Park, T., Isola, P., and Efros, A.A. (2017, January 22\u201329). Unpaired image-to-image translation using cycle-consistent adversarial networks. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Venice, Italy.","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., and Aila, T. (2019, January 16\u201320). A style-based generator architecture for generative adversarial networks. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., and Aila, T. (2020, January 14\u201319). Analyzing and improving the image quality of StyleGAN. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref_17","unstructured":"Karras, T., Aittala, M., Laine, S., H\u00e4rk\u00f6nen, E., Hellsten, J., Lehtinen, J., and Aila, T. (2021, January 6\u201314). Alias-free generative adversarial networks. Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), Virtual Conference."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Duan, Y., Hong, Y., Niu, L., and Zhang, L. (2023, January 7\u201314). Few-shot defect image generation via defect-aware feature manipulation. Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), Washington, DC, USA.","DOI":"10.1609\/aaai.v37i1.25132"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Hu, T., Zhang, J., Yi, R., Du, Y., Chen, X., Liu, L., Wang, Y., and Wang, C. (2024, January 20\u201327). AnomalyDiffusion: Few-shot anomaly image generation with diffusion model. Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), Vancouver, BC, Canada.","DOI":"10.1609\/aaai.v38i8.28696"},{"key":"ref_20","first-page":"1611","article-title":"Defect image sample generation with GAN for improving defect recognition","volume":"17","author":"Niu","year":"2020","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Zhang, G., Cui, K., Hung, T.-Y., and Lu, S. (2021, January 5\u20139). Defect-GAN: High-fidelity defect synthesis for automated defect inspection. Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, USA.","DOI":"10.1109\/WACV48630.2021.00257"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"120284","DOI":"10.1016\/j.eswa.2023.120284","article-title":"Anomaly-GAN: A data augmentation method for train surface anomaly detection","volume":"228","author":"Liu","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Deng, F., Luo, J., Fu, L., Huang, Y., Chen, J., Li, N., Zhong, J., and Lam, T.L. (2024). DG2GAN: Improving defect recognition performance with generated defect image sample. Sci. Rep., 14.","DOI":"10.1038\/s41598-024-64716-y"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"130455","DOI":"10.1016\/j.neucom.2025.130455","article-title":"Defect image generation through feature disentanglement using StyleGAN2-ADA","volume":"647","author":"He","year":"2025","journal-title":"Neurocomputing"},{"key":"ref_25","unstructured":"Khanam, R., and Hussain, M. (2024). YOLOv11: An overview of the key architectural enhancements. arXiv."},{"key":"ref_26","unstructured":"Mo, S., Cho, M., and Shin, J. (2020). Freeze the discriminator: A simple baseline for fine-tuning GANs. arXiv."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Duan, Y., Niu, L., Hong, Y., and Zhang, L. (2024, January 20\u201327). WeditGAN: Few-shot image generation via latent space relocation. Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), Vancouver, BC, Canada.","DOI":"10.1609\/aaai.v38i2.27932"},{"key":"ref_28","unstructured":"Zhao, Y., Chandrasegaran, K., Abdollahzadeh, M., Du, C., Pang, T., Li, R., Ding, H., and Cheung, N.-M. (2023). AdAM: Few-shot image generation via adaptation-aware kernel modulation. arXiv."},{"key":"ref_29","unstructured":"Gal, R., Alaluf, Y., Atzmon, Y., Patashnik, O., Bermano, A.H., Chechik, G., and Cohen-Or, D. (2022). An image is worth one word: Personalizing text-to-image generation using textual inversion. arXiv."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., and Aberman, K. (2023, January 18\u201322). DreamBooth: Fine-tuning text-to-image diffusion models for subject-driven generation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"127837","DOI":"10.1016\/j.neucom.2024.127837","article-title":"Unveiling the potential of progressive training diffusion model for defect image generation and recognition in industrial processes","volume":"592","author":"Wang","year":"2024","journal-title":"Neurocomputing"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Jin, Y., Peng, J., He, Q., Hu, T., Wu, J., Chen, H., Wang, H., Zhu, W., Chi, M., and Liu, J. (2025, January 3\u20137). Dual-Interrelated Diffusion Model for Few-Shot Anomaly Image Generation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Denver, CO, USA.","DOI":"10.1109\/CVPR52734.2025.02832"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.-Y., and Kweon, I.S. (2018, January 8\u201314). CBAM: Convolutional block attention module. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"ref_34","unstructured":"Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., and Courville, A.C. (2017, January 4\u20139). Improved training of Wasserstein GANs. Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), Long Beach, CA, USA."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Mao, Q., Lee, H.-Y., Tseng, H.-Y., Ma, S., and Yang, M.-H. (2019, January 16\u201320). Mode seeking generative adversarial networks for diverse image synthesis. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00152"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Bergmann, P., Fauser, M., Sattlegger, D., and Steger, C. (2019, January 16\u201320). MVTec AD\u2014A comprehensive real-world dataset for unsupervised anomaly detection. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00982"},{"key":"ref_37","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., and Hochreiter, S. (2017, January 4\u20139). GANs trained by a two time-scale update rule converge to a local Nash equilibrium. Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), Long Beach, CA, USA."},{"key":"ref_38","unstructured":"Bi\u0144kowski, M., Sutherland, D.J., Arbel, M., and Gretton, A. (2018). Demystifying MMD GANs. arXiv."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., and Wang, O. (2018, January 18\u201323). The unreasonable effectiveness of deep features as a perceptual metric. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (2016, January 27\u201330). Rethinking the Inception architecture for computer vision. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.308"}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-433X\/11\/10\/367\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,18]],"date-time":"2025-10-18T04:40:00Z","timestamp":1760762400000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-433X\/11\/10\/367"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,16]]},"references-count":40,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2025,10]]}},"alternative-id":["jimaging11100367"],"URL":"https:\/\/doi.org\/10.3390\/jimaging11100367","relation":{},"ISSN":["2313-433X"],"issn-type":[{"value":"2313-433X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,16]]}}}