Benchmarking Deep Learning Classifiers for SAR Automatic Target Recognition

TL;DR

The paper tackles the challenge of deploying SAR ATR systems by benchmarking five deep learning classifiers—ResNet18/34/50, a Graph Neural Network (GNN), and Vision Transformer variants—across three diverse SAR datasets (MSTAR, SynthWakeSAR, GBSAR). It evaluates both performance (accuracy) and practicality (throughput, latency, parameter count, MACs, and model size) to reveal trade-offs and dataset-specific behaviors. The findings show that while GNNs excel in throughput and latency, large CNNs like ResNet variants often win on accuracy depending on the dataset, and SS-ViT tends to have smaller parameter footprints though sometimes at a cost to accuracy; no single model dominates all metrics. The work emphasizes the importance of dataset diversity and a cost-benefit approach when selecting models for SAR ATR, pointing to future directions in robustness to capture-parameter variations and adversarial perturbations.

Abstract

Synthetic Aperture Radar SAR Automatic Target Recognition ATR is a key technique of remote-sensing image recognition which can be supported by deep neural networks The existing works of SAR ATR mostly focus on improving the accuracy of the target recognition while ignoring the systems performance in terms of speed and storage which is critical to real-world applications of SAR ATR For decision-makers aiming to identify a proper deep learning model to deploy in a SAR ATR system it is important to understand the performance of different candidate deep learning models and determine the best model accordingly This paper comprehensively benchmarks several advanced deep learning models for SAR ATR with multiple distinct SAR imagery datasets Specifically we train and test five SAR image classifiers based on Residual Neural Networks ResNet18 ResNet34 ResNet50 Graph Neural Network GNN and Vision Transformer for Small-Sized Datasets (SS-ViT) We select three datasets MSTAR GBSAR and SynthWakeSAR that offer heterogeneity We evaluate and compare the five classifiers concerning their classification accuracy runtime performance in terms of inference throughput and analytical performance in terms of number of parameters number of layers model size and number of operations Experimental results show that the GNN classifier outperforms with respect to throughput and latency However it is also shown that no clear model winner emerges from all of our chosen metrics and a one model rules all case is doubtful in the domain of SAR ATR

Figures (1)

• Figure 1: Architecture of GNN-based SAR image classifier