Knowledge distillation: A novel approach for deep feature selection

Knowledge distillation: A novel approach for deep feature selection

High dimensional data in hyperspectral remote sensing leads to computational, analytical, and storage complexities. Dimensionality reduction serves as an efficient tool to remove redundant, irrelevant, and highly correlated features. Recently, deep learning approaches have received remarkable progre...

Full description

Bibliographic Details
Main Authors: Deepa C, Amba Shetty, Narasimhadhan A V
Format: Article
Language:English
Published: Elsevier 2023-02-01
Series:Egyptian Journal of Remote Sensing and Space Sciences
Subjects:
Dimensionality reduction
Hyperspectral data
Feature extraction
Knowledge distillation
Feature selection
Autoencoders
Online Access:http://www.sciencedirect.com/science/article/pii/S1110982322001181

Internet

http://www.sciencedirect.com/science/article/pii/S1110982322001181

Similar Items