Variational Temporal Deep Generative Model for Radar HRRP Target Recognition

TL;DR

This paper introduces a novel recurrent gamma belief network for radar target recognition using HRRP data, leveraging hierarchical gamma distributions and hybrid inference methods to improve classification accuracy and interpretability.

Contribution

It proposes a new deep generative model with supervised and unsupervised variants, enhancing discriminative feature extraction and computational efficiency for radar target recognition.

Findings

Efficient training and fast prediction demonstrated on synthetic and real data.

High classification accuracy and good generalization achieved.

Provides interpretable multi-layer latent representations.

Abstract

We develop a recurrent gamma belief network (rGBN) for radar automatic target recognition (RATR) based on high-resolution range profile (HRRP), which characterizes the temporal dependence across the range cells of HRRP. The proposed rGBN adopts a hierarchy of gamma distributions to build its temporal deep generative model. For scalable training and fast out-of-sample prediction, we propose the hybrid of a stochastic-gradient Markov chain Monte Carlo (MCMC) and a recurrent variational inference model to perform posterior inference. To utilize the label information to extract more discriminative latent representations, we further propose supervised rGBN to jointly model the HRRP samples and their corresponding labels. Experimental results on synthetic and measured HRRP data show that the proposed models are efficient in computation, have good classification accuracy and generalization ability, and provide highly interpretable multi-stochastic-layer latent structure.