3-D Hybrid CNN Combined With 3-D Generative Adversarial Network for Wetland Classification With Limited Training Data

3-D Hybrid CNN Combined With 3-D Generative Adversarial Network for Wetland Classification With Limited Training Data

Recently, deep learning algorithms, specifically convolutional neural networks (CNNs), have played an important role in remote sensing image classification, including wetland mapping. However, one limitation of deep CNN for classification is its requirement for a great number of training samples. Th...

Full description

Bibliographic Details
Main Authors: Ali Jamali, Masoud Mahdianpari, Fariba Mohammadimanesh, Brian Brisco, Bahram Salehi
Format: Article
Language:English
Published: IEEE 2022-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Convolutional neural network (CNN)
deep convolutional neural network (DCNN)
generative adversarial network (GAN)
random forest (RF)
wetland mapping
Online Access:https://ieeexplore.ieee.org/document/9903275/

Internet

https://ieeexplore.ieee.org/document/9903275/

Similar Items