EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Semi-Supervised Multi-Scale Convolutional Neural Network for Hyperspectral Image Classification with Limited Labeled Samples

Chen Yang, Zizhuo Liu, Renchu Guan, Haishi Zhao

Remote Sensing · 23.09.2025 · 17 (19) · 3273

DOI: 10.3390/rs17193273 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 23.09.2025. Verfasst von Chen Yang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 64 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Science-Technology Development Plan Project of Jilin Province of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Supervised deep learning methods have been widely utilized in hyperspectral image (HSI) classification tasks. However, acquiring a large number of reliably labeled samples to train deep networks is not always possible in practical HSI applications due to the time-consuming and laborious labeling process. Semi-supervised learning is commonly used in scenarios with insufficient labeled samples. However, semi-supervised models based on a pseudo-label strategy often suffer from error accumulation. To address this issue and improve HSI classification performance with few labeled samples, a semi-supervised deep learning approach is proposed. First, a multi-scale convolutional neural network with accurate discriminative capability is constructed to reduce pseudo-label errors. Then, a new pseudo-label generation strategy based on Dropout is presented, in which feature-level data augmentation is applied by considering multiple predictions of the unlabeled samples to mitigate the error accumulation problem. Finally, the multi-scale CNN and the new pseudo-label strategy are integrated into a unified model to improve HSI classification performance. The experimental results demonstrate that the proposed approach outperforms other semi-supervised methods in the literature on four real HSI datasets with limited labeled samples.

Förderung

  • National Natural Science Foundation of China
  • Science-Technology Development Plan Project of Jilin Province of China

Zitieren

APA

Yang, C., Liu, Z., Guan, R., & Zhao, H. (2025). A Semi-Supervised Multi-Scale Convolutional Neural Network for Hyperspectral Image Classification with Limited Labeled Samples. Remote Sensing, 17(19), 3273. https://doi.org/10.3390/rs17193273

Vancouver

Yang C, Liu Z, Guan R, Zhao H. A Semi-Supervised Multi-Scale Convolutional Neural Network for Hyperspectral Image Classification with Limited Labeled Samples. Remote Sensing. 2025;17(19):3273. doi:10.3390/rs17193273

BibTeX
@article{Yang2025,
  author = {Yang, Chen and Liu, Zizhuo and Guan, Renchu and Zhao, Haishi},
  title = {A Semi-Supervised Multi-Scale Convolutional Neural Network for Hyperspectral Image Classification with Limited Labeled Samples},
  journal = {Remote Sensing},
  year = {2025},
  volume = {17},
  number = {19},
  pages = {3273},
  doi = {10.3390/rs17193273}
}
Kostenlos starten →