Class factorized complex variational auto-encoder for HRR radar target recognition

•A class factorized complex variational auto-encoder is proposed and used for RATR.•Our model is a complex-valued neural network for utilizing the phase of HRR data.•Our method adopts class-decoders to depict the generation of data from each class.•The learned prior of the latent variable helps lear...

Full description

Bibliographic Details

Published in:	Signal processing Vol. 182; p. 107932
Main Authors:	Liao, Leiyao, Du, Lan, Chen, Jian
Format:	Journal Article
Language:	English
Published:	Elsevier B.V 01.05.2021
Subjects:	Complex-valued neural network (CV-NN) High range resolution (HRR) radar Minimum reconstruction error Radar automatic target recognition (RATR) Variational auto-encoder (VAE) Radar automatic target recognition (RATR) Complex-valued neural network (CV-NN) High range resolution (HRR) radar Variational auto-encoder (VAE) Minimum reconstruction error
ISSN:	0165-1684, 1872-7557
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!