EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Zero-Shot Image Classification Method of Ship Coating Defects Based on IDATLWGAN

Henan Bu, Teng Yang, Changzhou Hu, Xianpeng Zhu, Zikang Ge, Zhuwen Yan, Yingxin Tang

Coatings · 11.04.2024 · 14 (4) · 464

DOI: 10.3390/coatings14040464 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Coatings, online erschienen am 11.04.2024. Verfasst von Henan Bu und 6 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Industry and Information Technology High-Tech Ship Research Project, National Defense Basic Scientific Research Project, RO-RO Passenger Ship Efficient Construction Process and Key Technology Research.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In recent years, the defect image classification method based on deep transfer learning has been widely explored and researched, and the task of source and target domains with the same painting defect image class has been solved successfully. However, in real applications, due to the complexity and uncertainty of ship painting conditions, it is very likely that there are unknown classes of painting defects, and the traditional deep learning model cannot identify a few classes, which leads to model overfitting and reduces its generalization ability. In this paper, a zero-shot Image classification method for ship painting defects based on IDATLWGAN is proposed to identify new unknown classes of defects in the target domain. The method is based on a deep convolutional neural network combined with adversarial transfer learning. First, a preprocessed ship painting defect dataset is used as input for the domain-invariant feature extractor. Then, the domain invariant feature extractor takes domain invariant features from the source and target domains. Finally, Defect discriminators and domain alignment discriminators are employed to classify the known categories of unlabeled defects and unknown categories of unlabeled defects in the target domain and to further reduce the distance between the edge distributions of the source and target domains. The experimental results show that the proposed model in this paper extracts a better distribution of invariant features in the source and target domains compared to other existing transfer learning models. It can successfully complete the migration task and accurately recognize the painting defects of known categories and new unknown categories, which is a perfect combination of intelligent algorithms and engineering practice.

Förderung

  • Ministry of Industry and Information Technology High-Tech Ship Research Project
  • National Defense Basic Scientific Research Project
  • RO-RO Passenger Ship Efficient Construction Process and Key Technology Research

Zitieren

APA

Bu, H., Yang, T., Hu, C., Zhu, X., Ge, Z., Yan, Z., & Tang, Y. (2024). A Zero-Shot Image Classification Method of Ship Coating Defects Based on IDATLWGAN. Coatings, 14(4), 464. https://doi.org/10.3390/coatings14040464

Vancouver

Bu H, Yang T, Hu C, Zhu X, Ge Z, Yan Z, et al. A Zero-Shot Image Classification Method of Ship Coating Defects Based on IDATLWGAN. Coatings. 2024;14(4):464. doi:10.3390/coatings14040464

BibTeX
@article{Bu2024,
  author = {Bu, Henan and Yang, Teng and Hu, Changzhou and Zhu, Xianpeng and Ge, Zikang and Yan, Zhuwen and Tang, Yingxin},
  title = {A Zero-Shot Image Classification Method of Ship Coating Defects Based on IDATLWGAN},
  journal = {Coatings},
  year = {2024},
  volume = {14},
  number = {4},
  pages = {464},
  doi = {10.3390/coatings14040464}
}
Kostenlos starten →