Abstract
Hyperspectral image analysis plays an important role in agriculture, mineral industry, and for military purposes. However, it is quite challenging when classifying high-dimensional hyperspectral data with few labeled samples. Currently, generative adversarial networks (GANs) have been widely used for sample generation, but it is difficult to acquire high-quality samples with unwanted noises and uncontrolled divergences. 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. To demonstrate the effectiveness of the proposed SaGAAN, we tested it on two well-known hyperspectral datasets: Pavia University and Indian Pines. The experiment results illustrate that the proposed method can greatly improve the classification accuracy, even with a small number of initial labeled samples.
Highlights
With the fast development of remote sensing technology, hyperspectral sensors are able to capture high spatial resolution images with hundreds of spectral bands, such as those on the recently launched satellites Zhuhai and Gaofen-5
To solve the above problems, in this paper, we propose the self-attention generative adversarial adaptation network (SaGAAN) to generate high quality labeled samples in the spectral domain for hyperspectral image classification
ReLu a Att is self-attention layer; b The first four layers of discriminator are used for domain adaptation; c The first five layers of discriminator are used for image classification. c represents the number of classes
Summary
With the fast development of remote sensing technology, hyperspectral sensors are able to capture high spatial resolution images with hundreds of spectral bands, such as those on the recently launched satellites Zhuhai and Gaofen-5. Complementary, the convolutional neural network (CNN) uses receptive fields to explore effective features from both spectral and spatial domains To enhance this capability, derivative deep models such as ResNet, VGG, FCN, and U-Net have successfully applied in hyperspectral image classification. The generative adversarial networks (GANs) aims to mimic and produce high-quality realistic data to increase the number of training samples. To enrich the training samples for hyperspectral image classification, an unsupervised 1D GAN was proposed to capture the spectral distribution [7]. To solve the above problems, in this paper, we propose the self-attention generative adversarial adaptation network (SaGAAN) to generate high quality labeled samples in the spectral domain for hyperspectral image classification.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
