Journal
IEEE TRANSACTIONS ON CYBERNETICS
Volume 50, Issue 7, Pages 3318-3329Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TCYB.2019.2915094
Keywords
Gallium nitride; Deep learning; Training; Generators; Generative adversarial networks; Data models; Hyperspectral imaging; Conditional random fields (CRFs); generative adversarial networks (GANs); hyperspectral image (HSI) classification; semisupervised deep learning
Categories
Funding
- Canada Research Chairs Program
- Natural Sciences and Engineering Research Council of Canada
- China Scholarship Council
Ask authors/readers for more resources
In this paper, we address the hyperspectral image (HSI) classification task with a generative adversarial network and conditional random field (GAN-CRF)-based framework, which integrates a semisupervised deep learning and a probabilistic graphical model, and make three contributions. First, we design four types of convolutional and transposed convolutional layers that consider the characteristics of HSIs to help with extracting discriminative features from limited numbers of labeled HSI samples. Second, we construct semisupervised generative adversarial networks (GANs) to alleviate the shortage of training samples by adding labels to them and implicitly reconstructing real HSI data distribution through adversarial training. Third, we build dense conditional random fields (CRFs) on top of the random variables that are initialized to the softmax predictions of the trained GANs and are conditioned on HSIs to refine classification maps. This semisupervised framework leverages the merits of discriminative and generative models through a game-theoretical approach. Moreover, even though we used very small numbers of labeled training HSI samples from the two most challenging and extensively studied datasets, the experimental results demonstrated that spectral-spatial GAN-CRF (SS-GAN-CRF) models achieved top-ranking accuracy for semisupervised HSI classification.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available