EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

IGNN: An improved graph neufral network with integrated attention and pre-message-passing for few-shot image classification

Jianxiong Chen iD, Bingwei Fu, Lin Zou iD

PLOS One · 28.04.2026 · 21 (4) · e0348057

DOI: 10.1371/journal.pone.0348057 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 28.04.2026. Verfasst von Jianxiong Chen und 2 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Data Science and Behavioral Science, Civil Aviation Flight University of China, Guanghan, China. Hauptthemen laut MEDLINE: Graph Neural Networks, Image Processing, Computer-Assisted. Die Arbeit nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Sichuan Province Science and Technology Support Program, Fundamental Research Funds for the Central Universities.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Graph Neural Network (GNN) faces limitations in few-shot image classification due to insufficient adaptive feature extraction and limited long-range dependency modeling. To address these challenges, this study proposes an Improved Graph Neural Network (IGNN) integrating two key innovations. Firstly, we design an Attention-Enhanced Feature Extraction module, which combines Efficient Channel Attention (ECA) and self-attention mechanisms, enabling the model to dynamically focus on discriminative intra-image details and inter-image contextual relationships, thereby improving feature representation robustness. Secondly, we introduce a gated recurrent unit (GRU)-based Pre-message-passing mechanism, which establishes cross-sample associations between support and query sets before message propagation, effectively capturing long-range dependencies and mitigating information smoothing. The experimental results of three public datasets demonstrate that our proposed framework outperforms the existing methods and shows significant potential. It offers a pragmatic tool for applications requiring rapid adaptation to limited data, such as remote sensing and medical image analysis.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Graph Neural NetworksImage Processing, Computer-AssistedAlgorithmsHumansRecurrent Neural Networks

Autor:innen und Institutionen

  • Institute of Data Science and Behavioral Science, Civil Aviation Flight University of China, Guanghan, China.
  • Faculty of Science, Civil Aviation Flight University of China, Guanghan, China.

ORCID-Profile: Jianxiong Chen, Lin Zou

Förderung

  • Sichuan Province Science and Technology Support Program
  • Fundamental Research Funds for the Central Universities

Zitieren

APA

Chen, J., Fu, B., & Zou, L. (2026). IGNN: An improved graph neufral network with integrated attention and pre-message-passing for few-shot image classification. PLOS One, 21(4), e0348057. https://doi.org/10.1371/journal.pone.0348057

Vancouver

Chen J, Fu B, Zou L. IGNN: An improved graph neufral network with integrated attention and pre-message-passing for few-shot image classification. PLOS One. 2026;21(4):e0348057. doi:10.1371/journal.pone.0348057

BibTeX
@article{Chen2026,
  author = {Chen, Jianxiong and Fu, Bingwei and Zou, Lin},
  title = {IGNN: An improved graph neufral network with integrated attention and pre-message-passing for few-shot image classification},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {4},
  pages = {e0348057},
  doi = {10.1371/journal.pone.0348057}
}
Kostenlos starten →