Soft Segmented Randomization: Enhancing Domain Generalization in SAR-ATR for Synthetic-to-Measured

TL;DR

This paper introduces a novel soft segmented randomization framework that improves domain generalization in SAR-ATR by reducing discrepancies between synthetic and real data, enhancing model robustness in real-world scenarios.

Contribution

The paper proposes a new soft segmented randomization method that aligns synthetic data with real data distributions, improving SAR-ATR performance without extensive real data.

Findings

Significant performance improvement on measured SAR data

Effective reduction of synthetic-real domain gap

Robustness in limited or no measured data scenarios

Abstract

Synthetic aperture radar technology is crucial for high-resolution imaging under various conditions; however, the acquisition of real-world synthetic aperture radar data for deep learning-based automatic target recognition remains challenging due to high costs and data availability issues. To overcome these challenges, synthetic data generated through simulations have been employed, although discrepancies between synthetic and real data can degrade model performance. In this study, we introduce a novel framework, soft segmented randomization, designed to reduce domain discrepancy and improve the generalize ability of synthetic aperture radar automatic target recognition models. The soft segmented randomization framework applies a Gaussian mixture model to segment target and clutter regions softly, introducing randomized variations that align the synthetic data's statistical properties more closely with those of real-world data. Experimental results demonstrate that the proposed soft segmented randomization framework significantly enhances model performance on measured synthetic aperture radar data, making it a promising approach for robust automatic target recognition in scenarios with limited or no access to measured data.