A Developed Siamese CNN with 3D Adaptive Spatial-Spectral Pyramid Pooling for Hyperspectral Image Classification

A Developed Siamese CNN with 3D Adaptive Spatial-Spectral Pyramid Pooling for Hyperspectral Image Classification

Since hyperspectral images (HSI) captured by different sensors often contain different number of bands, but most of the convolutional neural networks (CNN) require a fixed-size input, the generalization capability of deep CNNs to use heterogeneous input to achieve better classification performance h...

Full description

Bibliographic Details
Main Authors: Mengbin Rao, Ping Tang, Zheng Zhang
Format: Article
Language:English
Published: MDPI AG 2020-06-01
Series:Remote Sensing
Subjects:
Siamese Convolutional Neural Network (SCNN)
three-dimensional adaptive spatial-spectral pyramid pooling (3D ASSP)
transfer learning
hyperspectral image classification
limited labeled samples
Online Access:https://www.mdpi.com/2072-4292/12/12/1964

Internet

https://www.mdpi.com/2072-4292/12/12/1964

Similar Items