Abstract
Recently, deep learning has achieved breakthroughs in hyperspectral image (HSI) classification. Deep-learning-based classifiers require a large number of labeled samples for training to provide excellent performance. However, the availability of labeled data is limited due to the significant human resources and time costs of labeling hyperspectral data. Unsupervised learning for hyperspectral image classification has thus received increasing attention. In this paper, we propose a novel unsupervised framework based on a contrastive learning method and a transformer model for hyperspectral image classification. The experimental results prove that our model can efficiently extract hyperspectral image features in unsupervised situations.
Highlights
Compared with general images, hyperspectral images can provide more abundant pixel-level spectral information, since they contain hundreds of spectral bands
We introduce bootstrap your own latent (BYOL), a state-of-the-art contrastive learning framework, to hyperspectral image classification using a transformer architecture
We introduce a vision transformer into unsupervised hyperspectral image classification
Summary
Hyperspectral images can provide more abundant pixel-level spectral information, since they contain hundreds of spectral bands. Most of the representative learning methods are based on two models: an autoencoder [12] and generative adversarial network (GAN) [13] These two models both aim to map the training data to a certain distribution mode. Contrastive learning aims to discriminate different data instead of obtaining the data distribution feature It requires much less computational resources than the representative learning method. The models used in contrastive learning, mostly 2D CNNs, for computer vision tasks are not applicable in hyperspectral image processing. We introduce bootstrap your own latent (BYOL), a state-of-the-art contrastive learning framework, to hyperspectral image classification using a transformer architecture. The 3D CNNs for hyperspectral image classification need much more computational resources than 2D CNNs for computer vision, and fail to process sequential data well.
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
