IEEE - Institute of Electrical and Electronics Engineers, Inc. - Hyperspectral Image Classification Using Random Occlusion Data Augmentation

Author(s): Juan Mario Haut ; Mercedes E. Paoletti ; Javier Plaza ; Antonio Plaza ; Li Plaza
Sponsor(s): IEEE Geoscience and Remote Sensing Society
Publisher: IEEE - Institute of Electrical and Electronics Engineers, Inc.
Publication Date: 1 November 2019
Volume: 16
Page(s): 1,751 - 1,755
ISSN (Electronic): 1558-0571
ISSN (Paper): 1545-598X
DOI: 10.1109/LGRS.2019.2909495
Regular:

Convolutional neural networks (CNNs) have become a powerful tool for remotely sensed hyperspectral image (HSI) classification due to their great generalization ability and high accuracy. However,... View More

Advertisement