EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Class-Discrepancy Dynamic Weighting for Cross-Domain Few-Shot Hyperspectral Image Classification

Chen Ding, Jiahao Yue, Sirui Zheng, Yizhuo Dong, Wenqiang Hua, Xueling Chen, Yu Xie, Song Yan, Wei Wei, Lei Zhang

Remote Sensing · 27.07.2025 · 17 (15) · 2605

DOI: 10.3390/rs17152605 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 27.07.2025. Verfasst von Chen Ding und 9 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Foundation, Science and Technology Department of Shaanxi Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In recent years, cross-domain few-shot learning (CDFSL) has demonstrated remarkable performance in hyperspectral image classification (HSIC), partially alleviating the distribution shift problem. However, most domain adaptation methods rely on similarity metrics to establish cross-domain class matching, making it difficult to simultaneously account for intra-class sample size variations and inherent inter-class differences. To address this problem, existing studies have introduced a class weighting mechanism within the prototype network framework, determining class weights by calculating inter-sample similarity through distance metrics. However, this method suffers from a dual limitation: susceptibility to noise interference and insufficient capacity to capture global class variations, which may lead to distorted weight allocation and consequently result in alignment bias. To solve these issues, we propose a novel class-discrepancy dynamic weighting-based cross-domain FSL (CDDW-CFSL) framework. It integrates three key components: (1) the class-weighted domain adaptation (CWDA) method dynamically measures cross-domain distribution shifts using global class mean discrepancies. It employs discrepancy-sensitive weighting to strengthen the alignment of critical categories, enabling accurate domain adaptation while maintaining feature topology; (2) the class mean refinement (CMR) method incorporates class covariance distance to compute distribution discrepancies between support set samples and class prototypes, enabling the precise capture of cross-domain feature internal structures; (3) a novel multi-dimensional feature extractor that captures both local spatial details and continuous spectral characteristics simultaneously, facilitating deep cross-dimensional feature fusion. The results in three publicly available HSIC datasets show the effectiveness of the CDDW-CFSL.

Förderung

  • National Natural Science Foundation of China
  • National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Foundation
  • Science and Technology Department of Shaanxi Province
  • Shaanxi Provincial Department of Education

Zitieren

APA

Ding, C., Yue, J., Zheng, S., Dong, Y., Hua, W., Chen, X., Xie, Y., Yan, S., Wei, W., & Zhang, L. (2025). Class-Discrepancy Dynamic Weighting for Cross-Domain Few-Shot Hyperspectral Image Classification. Remote Sensing, 17(15), 2605. https://doi.org/10.3390/rs17152605

Vancouver

Ding C, Yue J, Zheng S, Dong Y, Hua W, Chen X, et al. Class-Discrepancy Dynamic Weighting for Cross-Domain Few-Shot Hyperspectral Image Classification. Remote Sensing. 2025;17(15):2605. doi:10.3390/rs17152605

BibTeX
@article{Ding2025,
  author = {Ding, Chen and Yue, Jiahao and Zheng, Sirui and Dong, Yizhuo and Hua, Wenqiang and Chen, Xueling and Xie, Yu and Yan, Song and Wei, Wei and Zhang, Lei},
  title = {Class-Discrepancy Dynamic Weighting for Cross-Domain Few-Shot Hyperspectral Image Classification},
  journal = {Remote Sensing},
  year = {2025},
  volume = {17},
  number = {15},
  pages = {2605},
  doi = {10.3390/rs17152605}
}
Kostenlos starten →