An Interpretable Two-Stage Feature Decomposition Method for Deep Learning-based SAR ATR

TL;DR

This paper introduces a physics-based two-stage feature decomposition method for deep learning-based SAR ATR that enhances interpretability by transforming deep features into physically meaningful attribute scattering center components, while maintaining high recognition accuracy.

Contribution

It proposes a novel two-stage decomposition approach combining clustering and multilayer orthogonal NMF to produce interpretable features with physical meanings in SAR ATR.

Findings

Effective in transforming deep features into physically meaningful components.

Achieves high recognition accuracy comparable to state-of-the-art methods.

Demonstrates strong generalization across multiple benchmark datasets.

Abstract

Synthetic aperture radar automatic target recognition (SAR ATR) has seen significant performance improvements with deep learning. However, the black-box nature of deep SAR ATR introduces low confidence and high risks in decision-critical SAR applications, hindering practical deployment. To address this issue, deep SAR ATR should provide an interpretable reasoning basis $r_b$ and logic $\lambda_w$, forming the reasoning logic $\sum_{i} {{r_b^i} \times {\lambda_w^i}} =pred$ behind the decisions. Therefore, this paper proposes a physics-based two-stage feature decomposition method for interpretable deep SAR ATR, which transforms uninterpretable deep features into attribute scattering center components (ASCC) with clear physical meanings. First, ASCCs are obtained through a clustering algorithm. To extract independent physical components from deep features, we propose a two-stage decomposition method. In the first stage, a feature decoupling and discrimination module separates deep features into approximate ASCCs with global discriminability. In the second stage, a multilayer orthogonal non-negative matrix tri-factorization (MLO-NMTF) further decomposes the ASCCs into independent components with distinct physical meanings. The MLO-NMTF elegantly aligns with the clustering algorithms to obtain ASCCs. Finally, this method ensures both an interpretable reasoning process and accurate recognition results. Extensive experiments on four benchmark datasets confirm its effectiveness, showcasing the method's interpretability, robust recognition performance, and strong generalization capability.