Studying the Effects of Self-Attention on SAR Automatic Target Recognition

TL;DR

This paper explores how self-attention mechanisms improve SAR automatic target recognition by focusing on key image features, leading to higher accuracy, robustness, and explainability in noisy SAR data.

Contribution

It demonstrates that integrating attention modules enhances SAR ATR models' accuracy, robustness, and interpretability, addressing challenges of noise and background clutter.

Findings

Increased top-1 accuracy on MSTAR dataset

Enhanced robustness to noisy data

Improved model explainability

Abstract

Attention mechanisms are critically important in the advancement of synthetic aperture radar (SAR) automatic target recognition (ATR) systems. Traditional SAR ATR models often struggle with the noisy nature of the SAR data, frequently learning from background noise rather than the most relevant image features. Attention mechanisms address this limitation by focusing on crucial image components, such as the shadows and small parts of a vehicle, which are crucial for accurate target classification. By dynamically prioritizing these significant features, attention-based models can efficiently characterize the entire image with a few pixels, thus enhancing recognition performance. This capability allows for the discrimination of targets from background clutter, leading to more practical and robust SAR ATR models. We show that attention modules increase top-1 accuracy, improve input robustness, and are qualitatively more explainable on the MSTAR dataset.