R 2 -Net: A Hybrid Meta-Learning Framework for Cross-Domain Few-Shot Industrial Defect Detection
Journal of Advanced Computational Intelligence and Intelligent Informatics · 20.07.2026 · 30 (4) · 1138-1149
DOI: 10.20965/jaciii.2026.p1138 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Advanced Computational Intelligence and Intelligent Informatics, online erschienen am 20.07.2026. Verfasst von Ziyi Huang und 3 weiteren Autor:innen. Die Arbeit nennt 35 Literaturangaben. Gefördert von: Guangdong Province, University-Enterprise Joint Research and Development Center, Shenzhen Polytechnic.
Abstract (Originalsprache)
Few-shot industrial defect detection is critically challenged by poor cross-domain generalization, where models often fail to adapt from a source domain to new target domains. Existing meta-learning paradigms also face significant constraints in addressing this. Metric-based methods are prone to overfitting, while optimization-based approaches often suffer from high computational costs and training instability. To this end, we propose R 2 -Net, a hybrid meta-learning framework that balances performance and efficiency. Its core contribution lies in resolving the aforementioned dilemma through a synergy of optimization and inference: we employ the efficient first-order meta-optimizer Reptile to learn a high-quality set of meta-initial parameters. Building on this foundation, the model utilizes a backbone network integrated with an attention mechanism to extract high-quality features, which are then fed into a relation network for rapid and fine-grained relational defect inference. Experimental results on the MVTec AD and NEU-CLS datasets demonstrate that our framework significantly outperforms a range of strong baseline models in cross-domain few-shot tasks, validating its effectiveness.
Förderung
- Guangdong Province
- University-Enterprise Joint Research and Development Center
- Shenzhen Polytechnic
- National Natural Science Foundation of China
- Shenzhen Science and Technology Program
Zitieren
APA
Huang, Z., Ouyang, X., Zhang, H., & Yang, J. (2026). R 2 -Net: A Hybrid Meta-Learning Framework for Cross-Domain Few-Shot Industrial Defect Detection. Journal of Advanced Computational Intelligence and Intelligent Informatics, 30(4), 1138-1149. https://doi.org/10.20965/jaciii.2026.p1138
Vancouver
Huang Z, Ouyang X, Zhang H, Yang J. R 2 -Net: A Hybrid Meta-Learning Framework for Cross-Domain Few-Shot Industrial Defect Detection. Journal of Advanced Computational Intelligence and Intelligent Informatics. 2026;30(4):1138-1149. doi:10.20965/jaciii.2026.p1138
BibTeX
@article{Huang2026,
author = {Huang, Ziyi and Ouyang, Xinyu and Zhang, Haigang and Yang, Jinfeng},
title = {R 2 -Net: A Hybrid Meta-Learning Framework for Cross-Domain Few-Shot Industrial Defect Detection},
journal = {Journal of Advanced Computational Intelligence and Intelligent Informatics},
year = {2026},
volume = {30},
number = {4},
pages = {1138--1149},
doi = {10.20965/jaciii.2026.p1138}
}
EUVIMED