MFN Decomposition and Related Metrics for High-Resolution Range Profiles Generative Models

TL;DR

This paper introduces a novel decomposition of high-resolution range profiles into mask, features, and noise, along with two metrics based on physical interpretation, to evaluate generative models in radar target recognition.

Contribution

It proposes a new HRRP decomposition method and two physically interpretable metrics for evaluating generated HRRP data, addressing limitations of existing black-box evaluation methods.

Findings

Metrics effectively discriminate between real and generated HRRP data.

Decomposition enhances understanding of HRRP components.

Proposed approach improves evaluation transparency and interpretability.

Abstract

High-resolution range profile (HRRP ) data are in vogue in radar automatic target recognition (RATR). With the interest in classifying models using HRRP, filling gaps in datasets using generative models has recently received promising contributions. Evaluating generated data is a challenging topic, even for explicit data like face images. However, the evaluation methods used in the state-ofthe-art of HRRP generation rely on classification models. Such models, called ''black-box'', do not allow either explainability on generated data or multi-level evaluation. This work focuses on decomposing HRRP data into three components: the mask, the features, and the noise. Using this decomposition, we propose two metrics based on the physical interpretation of those data. We take profit from an expensive dataset to evaluate our metrics on a challenging task and demonstrate the discriminative ability of those.