The Comparability of Model Fusion to Measured Data in Confuser Rejection

TL;DR

This paper investigates how model fusion compares to real measured data in the context of confuser rejection for synthetic SAR data, aiming to improve classification accuracy despite data limitations.

Contribution

It introduces an ensembling approach that leverages synthetic data and confuser rejection techniques to better classify known targets and reject unknown ones in SAR imaging.

Findings

Model fusion improves classification accuracy on synthetic SAR data.

Ensembling enhances the ability to reject unknown targets.

Synthetic data can be effectively used with confuser rejection for SAR classification.

Abstract

Data collection has always been a major issue in the modeling and training of large deep learning networks, as no dataset can account for every slight deviation we might see in live usage. Collecting samples can be especially costly for Synthetic Aperture Radar (SAR), limiting the amount of unique targets and operating conditions we are able to observe from. To counter this lack of data, simulators have been developed utilizing the shooting and bouncing ray method to allow for the generation of synthetic SAR data on 3D models. While effective, the synthetically generated data does not perfectly correlate to the measured data leading to issues when training models solely on synthetic data. We aim to use computational power as a substitution for this lack of quality measured data, by ensembling many models trained on synthetic data. Synthetic data is also not complete, as we do not know what targets might be present in a live environment. Therefore we need to have our ensembling techniques account for these unknown targets by applying confuser rejection in which our models will reject unknown targets it is presented with, and only classify those it has been trained on.