EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Vision Transformer-Based Ensemble Learning for Hyperspectral Image Classification

Jun Liu, Haoran Guo, Yile He, Huali Li

Remote Sensing · 02.11.2023 · 15 (21) · 5208

DOI: 10.3390/rs15215208 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 02.11.2023. Verfasst von Jun Liu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 22-mal zitiert (Crossref) und nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, 2022 Doctoral Research Initiation Fund of Hunan University of Chinese Medicine, Hunan Provincial Department of Education Scientific Research.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Hyperspectral image (HSI) classification, due to its characteristic combination of images and spectra, has important applications in various fields through pixel-level image classification. The fusion of spatial–spectral features is a topic of great interest in the context of hyperspectral image classification, which typically requires selecting a larger spatial neighborhood window, potentially leading to overlaps between training and testing samples. Vision Transformer (ViTs), with their powerful global modeling abilities, have had a significant impact in the field of computer vision through various variants. In this study, an ensemble learning framework for HSI classification is proposed by integrating multiple variants of ViTs, achieving high-precision pixel-level classification. Firstly, the spatial shuffle operation was introduced to preprocess the training samples for HSI classification. By randomly shuffling operations using smaller spatial neighborhood windows, a greater potential spatial distribution of pixels can be described. Then, the training samples were transformed from a 3D cube to a 2D image, and a learning framework was built by integrating seven ViT variants. Finally, a two-level ensemble strategy was employed to achieve pixel-level classification based on the results of multiple ViT variants. Our experimental results demonstrate that the proposed ensemble learning framework achieves stable and significantly high classification accuracy on multiple publicly available HSI datasets. The proposed method also shows notable classification performance with varying numbers of training samples. Moreover, herein, it is proven that the spatial shuffle operation plays a crucial role in improving classification accuracy. By introducing superior individual classifiers, the proposed ensemble framework is expected to achieve even better classification performance.

Förderung

  • National Natural Science Foundation of China
  • 2022 Doctoral Research Initiation Fund of Hunan University of Chinese Medicine
  • Hunan Provincial Department of Education Scientific Research

Zitieren

APA

Liu, J., Guo, H., He, Y., & Li, H. (2023). Vision Transformer-Based Ensemble Learning for Hyperspectral Image Classification. Remote Sensing, 15(21), 5208. https://doi.org/10.3390/rs15215208

Vancouver

Liu J, Guo H, He Y, Li H. Vision Transformer-Based Ensemble Learning for Hyperspectral Image Classification. Remote Sensing. 2023;15(21):5208. doi:10.3390/rs15215208

BibTeX
@article{Liu2023,
  author = {Liu, Jun and Guo, Haoran and He, Yile and Li, Huali},
  title = {Vision Transformer-Based Ensemble Learning for Hyperspectral Image Classification},
  journal = {Remote Sensing},
  year = {2023},
  volume = {15},
  number = {21},
  pages = {5208},
  doi = {10.3390/rs15215208}
}
Kostenlos starten →