Next Article in Journal
A Novel Motion Compensation Scheme for Airborne Very High Resolution SAR
Previous Article in Journal
An Adaptive Piecewise Harmonic Analysis Method for Reconstructing Multi-Year Sea Surface Chlorophyll-A Time Series
Article

Prototype Calibration with Feature Generation for Few-Shot Remote Sensing Image Scene Classification

by 1,2,†, 1,*,†, 1, 1 and 3
1
School of Electronics and Information, Northwestern Polytechnical University, Xi’an 710072, China
2
Honors College, Northwestern Polytechnical University, Xi’an 710072, China
3
Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, USA
*
Author to whom correspondence should be addressed.
These authors contributed equally to this work.
Academic Editor: Pedro Melo-Pinto
Remote Sens. 2021, 13(14), 2728; https://doi.org/10.3390/rs13142728
Received: 19 June 2021 / Revised: 7 July 2021 / Accepted: 9 July 2021 / Published: 12 July 2021
Few-shot classification of remote sensing images has attracted attention due to its important applications in various fields. The major challenge in few-shot remote sensing image scene classification is that limited labeled samples can be utilized for training. This may lead to the deviation of prototype feature expression, and thus the classification performance will be impacted. To solve these issues, a prototype calibration with a feature-generating model is proposed for few-shot remote sensing image scene classification. In the proposed framework, a feature encoder with self-attention is developed to reduce the influence of irrelevant information. Then, the feature-generating module is utilized to expand the support set of the testing set based on prototypes of the training set, and prototype calibration is proposed to optimize features of support images that can enhance the representativeness of each category features. Experiments on NWPU-RESISC45 and WHU-RS19 datasets demonstrate that the proposed method can yield superior classification accuracies for few-shot remote sensing image scene classification. View Full-Text
Keywords: few-shot learning; remote sensing classification; feature learning; scene classification; prototype calibration few-shot learning; remote sensing classification; feature learning; scene classification; prototype calibration
Show Figures

Graphical abstract

MDPI and ACS Style

Zeng, Q.; Geng, J.; Huang, K.; Jiang, W.; Guo, J. Prototype Calibration with Feature Generation for Few-Shot Remote Sensing Image Scene Classification. Remote Sens. 2021, 13, 2728. https://doi.org/10.3390/rs13142728

AMA Style

Zeng Q, Geng J, Huang K, Jiang W, Guo J. Prototype Calibration with Feature Generation for Few-Shot Remote Sensing Image Scene Classification. Remote Sensing. 2021; 13(14):2728. https://doi.org/10.3390/rs13142728

Chicago/Turabian Style

Zeng, Qingjie, Jie Geng, Kai Huang, Wen Jiang, and Jun Guo. 2021. "Prototype Calibration with Feature Generation for Few-Shot Remote Sensing Image Scene Classification" Remote Sensing 13, no. 14: 2728. https://doi.org/10.3390/rs13142728

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop