Sample Generation with Self-Attention Generative Adversarial Adaptation Network (SaGAAN) for Hyperspectral Image Classification
Published in Remote Sensing, 2020
Recommended citation: Wenzhi Zhao, et al. (2019). "Sample Generation with Self-Attention Generative Adversarial Adaptation Network (SaGAAN) for Hyperspectral Image Classification." Remote Sensing. 12(5). https://www.mdpi.com/2072-4292/12/5/843
To generate high-quality hyperspectral samples, a self-attention generative adversarial adaptation network (SaGAAN) is proposed in this work. It aims to increase the number and quality of training samples to avoid the impact of over-fitting. Compared to the traditional GANs, the proposed method has two contributions:(1) it includes a domain adaptation term to constrain generated samples to be more realistic to the original ones; and (2) it uses the self-attention mechanism to capture the long-range dependencies across the spectral bands and further improve the quality of generated samples.
Recommended citation: Wenzhi Zhao, et al. (2019). “Sample Generation with Self-Attention Generative Adversarial Adaptation Network (SaGAAN) for Hyperspectral Image Classification” Remote Sensing. 12(5).