article · IOP Conference Series Earth and Environmental Science · 2021
CBS-GAN: A Band Selection Based Generative Adversarial Net for Hyperspectral Sample Generation
Yulin Qiao, Mostofa Zaman Mohammad, Yi Li, Xiaobo Liu, Zhihua Cai
Cited by 2Open access
Abstract
Abstract Sample generation is an effective method to improve the performance of hyperspectral image classification by generating virtual samples for training sample expansion in the training process of classification. However, there are some defects existing in the previous sample generation methods including the lack of spatial information, the redundant generation and the damage of the original spectral components. In this paper, we propose conditional band selection generative adversarial net, named CBS-GAN, to handle this problem. Firstly, the band selection net of CBS-GAN is utilized to avoid redundant bands and keep original spectral information, then the generation net of CBS-GAN generates the spatial-spectral data blocks by selected bands for sample generation. The experiments of classification are also used to demonstrate the availability of virtual samples generated by our method.
Cite this paper
Qiao, Y., Mohammad, M. Z., Li, Y., Liu, X., & Cai, Z. (2021). CBS-GAN: A Band Selection Based Generative Adversarial Net for Hyperspectral Sample Generation. IOP Conference Series Earth and Environmental Science, 734(1), 012035. https://doi.org/10.1088/1755-1315/734/1/012035
Qiao, Yulin, et al. “CBS-GAN: A Band Selection Based Generative Adversarial Net for Hyperspectral Sample Generation.” IOP Conference Series Earth and Environmental Science, vol. 734, no. 1, 2021, p. 012035, https://doi.org/10.1088/1755-1315/734/1/012035.
Qiao, Yulin, Mostofa Zaman Mohammad, Yi Li, Xiaobo Liu, and Zhihua Cai. 2021. “CBS-GAN: A Band Selection Based Generative Adversarial Net for Hyperspectral Sample Generation.” IOP Conference Series Earth and Environmental Science 734 (1): 012035. https://doi.org/10.1088/1755-1315/734/1/012035.
Qiao, Y. et al. (2021) ‘CBS-GAN: A Band Selection Based Generative Adversarial Net for Hyperspectral Sample Generation’, IOP Conference Series Earth and Environmental Science, 734(1), p. 012035. Available at: https://doi.org/10.1088/1755-1315/734/1/012035.
@article{qiao2021band,
title = {{CBS-GAN: A Band Selection Based Generative Adversarial Net for Hyperspectral Sample Generation}},
author = {Qiao, Yulin and Mohammad, Mostofa Zaman and Li, Yi and Liu, Xiaobo and Cai, Zhihua},
journal = {IOP Conference Series Earth and Environmental Science},
volume = {734},
number = {1},
pages = {012035},
year = {2021},
doi = {10.1088/1755-1315/734/1/012035}
}Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.