EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

ImbDef-GAN: Defect Image-Generation Method Based on Sample Imbalance

Dengbiao Jiang, Nian Tao, Kelong Zhu, Yiming Wang, Haijian Shao iD

Journal of Imaging · 16.10.2025 · 11 (10) · 367

DOI: 10.3390/jimaging11100367 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 16.10.2025. Verfasst von Dengbiao Jiang und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science, Jiangsu University of Science and Technology, Zhenjiang 212003, China. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Schlagwörter

Stichwörter der Autor:innen

background image generationdeep learningdefect featuresdefect image generationsample imbalance

Autor:innen und Institutionen

  • School of Computer Science, Jiangsu University of Science and Technology, Zhenjiang 212003, China.
  • Tofflon Science & Technology Group Co., Ltd., Shanghai 200000, China.

ORCID-Profile: Haijian Shao

Zitieren

APA

Jiang, D., Tao, N., Zhu, K., Wang, Y., & Shao, H. (2025). ImbDef-GAN: Defect Image-Generation Method Based on Sample Imbalance. Journal of Imaging, 11(10), 367. https://doi.org/10.3390/jimaging11100367

Vancouver

Jiang D, Tao N, Zhu K, Wang Y, Shao H. ImbDef-GAN: Defect Image-Generation Method Based on Sample Imbalance. Journal of Imaging. 2025;11(10):367. doi:10.3390/jimaging11100367

BibTeX
@article{Jiang2025,
  author = {Jiang, Dengbiao and Tao, Nian and Zhu, Kelong and Wang, Yiming and Shao, Haijian},
  title = {ImbDef-GAN: Defect Image-Generation Method Based on Sample Imbalance},
  journal = {Journal of Imaging},
  year = {2025},
  volume = {11},
  number = {10},
  pages = {367},
  doi = {10.3390/jimaging11100367}
}
Kostenlos starten →