Skip to search boxSkip to navigationSkip to main content

Few-shot hyperspectral remote sensing image classification via an ensemble of meta-optimizers with update integration

  • Tao Hao
    ,
  • Zhihua Zhang
    ,
  • James Crabbe
  • Shandong University
    ,
  • University of Oxford
Research Output: Contribution to journal Article Peer-review

Open access

Abstract

Hyperspectral images (HSIs) with abundant spectra and high spatial resolution can satisfy the demand for the classification of adjacent homogeneous regions and accurately determine their specific land-cover classes. Due to the potentially large variance within the same class in hyperspectral images, classifying HSIs with limited training samples (i.e., few-shot HSI classification) has become especially difficult. To solve this issue without adding training costs, we propose an ensemble of meta-optimizers that were generated one by one through utilizing periodic annealing on the learning rate during the meta-training process. Such a combination of meta-learning and ensemble learning demonstrates a powerful ability to optimize the deep network on few-shot HSI training. In order to further improve the classification performance, we introduced a novel update integration process to determine the most appropriate update for network parameters during the model training process. Compared with popular human-designed optimizers (Adam, AdaGrad, RMSprop, SGD, etc.), our proposed model performed better in convergence speed, final loss value, overall accuracy, average accuracy, and Kappa coefficient on five HSI benchmarks in a few-shot learning setting.

Publication Information

Output type

Research Output: Contribution to journal Article Peer-review

Original language

English

Article number

2988

Journal (Volume, Issue Number)

Remote Sensing (Volume 16, Issue 16)

Publication milestones

  • Accepted/In press - 13/08/2024
  • Published - 14/08/2024

Publication status

Published - 14/08/2024

External Publication IDs

  • handle.net: 10547/626352
  • Scopus: 85202450072

Access to documents

Publication metrics

Metrics

Download statistics
Download count
2

PlumX, opens in new tab

4
Mentions
2
Captures
2