EUVIMEDScopri EUVIMED
Open access · CC BY 4.0

Class-Patch Similarity Weighted Embedding for Few-Shot Infrared Image Classification

Zhen Huang, Jinfu Gong, Xiaoyu Wang, Dongjie Wu, Yong Zhang

Electronics · 2025-01-13 · 14 (2) · 290

DOI: 10.3390/electronics14020290 ↗

At a glance

Journal article in Electronics, published online on 2025-01-13. Written by Zhen Huang and 4 co-authors. Cited 2 times so far (Crossref); 43 references. The full text is freely available (open access, CC BY 4.0).

AbstractDati bibliograficiCiteRelated studies

Abstract (original language)

Infrared imaging plays a vital role in critical surveillance, military reconnaissance, and industrial inspection applications due to its advantages such as strong concealment and the ability to operate around the clock. However, the combination of low infrared image resolution and complex background scenarios poses significant challenges for traditional deep learning models in accurately extracting the most discriminative features for classification. These models are often disrupted by irrelevant features, especially when data for new classes is scarce. Current few-shot learning approaches heavily rely on comparing image patches, but the scarcity of data can significantly degrade the performance of recognition algorithms. To address these challenges, we propose the Class Patch Similarity Weighted Embedding (CPSWE) framework for few-shot infrared target classification. The CPSWE framework employs a ViT architecture for feature extraction. By introducing class embeddings and calculating similarity-based weights for each patch, CPSWE reweights the patch features to enhance their relevance to the target class. This approach improves the discriminability of class-related features, leading to better generalization in few-shot settings. Furthermore, we introduce an infrared dataset specifically designed for few-shot learning, combining multiple open-source datasets to support research in this area. Extensive experiments on the few-shot learning benchmark dataset miniImageNet and the infrared dataset miniIRNet show that CPSWE outperforms existing few-shot learning methods, achieving significant improvements in classification accuracy on infrared image datasets with limited labeled samples.

Cite

APA

Huang, Z., Gong, J., Wang, X., Wu, D., & Zhang, Y. (2025). Class-Patch Similarity Weighted Embedding for Few-Shot Infrared Image Classification. Electronics, 14(2), 290. https://doi.org/10.3390/electronics14020290

Vancouver

Huang Z, Gong J, Wang X, Wu D, Zhang Y. Class-Patch Similarity Weighted Embedding for Few-Shot Infrared Image Classification. Electronics. 2025;14(2):290. doi:10.3390/electronics14020290

BibTeX
@article{Huang2025,
  author = {Huang, Zhen and Gong, Jinfu and Wang, Xiaoyu and Wu, Dongjie and Zhang, Yong},
  title = {Class-Patch Similarity Weighted Embedding for Few-Shot Infrared Image Classification},
  journal = {Electronics},
  year = {2025},
  volume = {14},
  number = {2},
  pages = {290},
  doi = {10.3390/electronics14020290}
}
Start for free →