Unsupervised SAR Imagery Feature Learning with Median Filter-Based Loss Value

Unsupervised SAR Imagery Feature Learning with Median Filter-Based Loss Value

The scarcity of open SAR (Synthetic Aperture Radars) imagery databases (especially the labeled ones) and sparsity of pre-trained neural networks lead to the need for heavy data generation, augmentation, or transfer learning usage. This paper described the characteristics of SAR imagery, the limitati...

Full description

Bibliographic Details
Main Author: Krzysztof Gromada
Format: Article
Language:English
Published: MDPI AG 2022-08-01
Series:Sensors
Subjects:
Synthetic Aperture Radar (SAR)
Convolutional Neural Networks (CNN)
Deep Neural Networks (DNN)
autoencoders (AE)
transfer learning
Automatic Target Recognition (ATR)
Online Access:https://www.mdpi.com/1424-8220/22/17/6519

Internet

https://www.mdpi.com/1424-8220/22/17/6519

Similar Items