EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Spatial–Spectral Prototype-Guided Deep SMOTE for Imbalanced Hyperspectral Image Classification

Yan Lv, Guanghao Kang, Yan Cao, Shiyu Wang, Liang Guo, Huaiwu Peng, Wei Feng

Remote Sensing · 28.10.2026 · 18 (21) · 3711

DOI: 10.3390/rs18213711 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 28.10.2026. Verfasst von Yan Lv und 6 weiteren Autor:innen. Die Arbeit nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key R&D Program of China, Natural Science Foundation of Ningxia Province of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The inherent class imbalance and scarcity of labeled samples remain major challenges in hyperspectral image (HSI) classification. SMOTE-based methods alleviate class imbalance by generating synthetic minority-class samples. However, their interpolation mechanisms often fail to capture spatial–spectral features adequately, resulting in noisy or boundary-ambiguous samples. To address this issue, this paper proposes Spatial–Spectral Prototype-guided Deep SMOTE (SSPD) for imbalanced HSI classification. Firstly, SSPD constructs a spatial–spectral representation guided by feature importance to suppress redundant spectral bands and isolated spatial noise. Secondly, SSPD employs a prototype-guided oversampling strategy to generate synthetic minority-class samples. Class prototypes determine the generation direction, while feature-importance weights constrain the interpolation process to preserve discriminative spectral responses. Finally, a stepwise ensemble with soft voting is employed to integrate classifiers trained under different imbalance ratios. Extensive experiments were conducted on Indian Pines, Pavia University, Salinas, and WHU-Hi benchmark datasets. Compared with the individual machine-learning classifiers, SSPD achieves more stable and competitive performance in terms of Overall Accuracy (OA), Average Accuracy (AA), and Kappa Coefficient (KC).

Förderung

  • National Key R&D Program of China
  • Natural Science Foundation of Ningxia Province of China

Zitieren

APA

Lv, Y., Kang, G., Cao, Y., Wang, S., Guo, L., Peng, H., & Feng, W. (2026). Spatial–Spectral Prototype-Guided Deep SMOTE for Imbalanced Hyperspectral Image Classification. Remote Sensing, 18(21), 3711. https://doi.org/10.3390/rs18213711

Vancouver

Lv Y, Kang G, Cao Y, Wang S, Guo L, Peng H, et al. Spatial–Spectral Prototype-Guided Deep SMOTE for Imbalanced Hyperspectral Image Classification. Remote Sensing. 2026;18(21):3711. doi:10.3390/rs18213711

BibTeX
@article{Lv2026,
  author = {Lv, Yan and Kang, Guanghao and Cao, Yan and Wang, Shiyu and Guo, Liang and Peng, Huaiwu and Feng, Wei},
  title = {Spatial–Spectral Prototype-Guided Deep SMOTE for Imbalanced Hyperspectral Image Classification},
  journal = {Remote Sensing},
  year = {2026},
  volume = {18},
  number = {21},
  pages = {3711},
  doi = {10.3390/rs18213711}
}
Kostenlos starten →