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

Authors

Chenwei Wang, Congwen Wu, Renjie Xu, Zhaoke Huang, Cunyi Yin, Deqing Mao, Sitong Zhang, Hong Yan

Published in

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. Volume PP. Sep 15, 2026. Epub Sep 15, 2026.

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 weights λ_w, forming the reasoning logic Σ _i rⁱ_b × λⁱ _w = pred behind the decisions. However, deep features are inherently abstract, high-dimensional, and entangled: standard DNN operations couple independent ASCs into uninterpretable representations, and directly decoupling them not only incurs large decomposition errors but also destroys discriminability. Therefore, this paper proposes a physics-based two-stage feature decomposition method for interpretable deep SAR ATR, which for the first time identifies and resolves the coupling-discriminability dilemma unique to SAR ATR by transforming entangled deep features into ASC components (ASCCs) with clear physical meanings. First, ASCCs are obtained through a clustering algorithm. To extract independent physical components from entangled 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 trifactorization (MLO-NMTF) further decomposes the ASCCs into independent components with distinct physical meanings. The MLO-NMTF with orthogonal constraints is proved equivalent, in the relaxed sense, to spectral clustering, establishing a structural correspondence between the network's latent space and the physical scattering domain, and underpinning the verifiable reasoning logic Σ _i rⁱ_b ×λⁱ _w = pred. Finally, this method ensures both a fully verifiable reasoning process and accurate recognition results. Extensive experiments on four benchmark datasets across 12 backbone architectures, compared against 9 interpretable SAR ATR methods, confirm its superior recognition performance and strong generalization capability.

PMID:
42743044
Bibliographic data and abstract were imported from PubMed on 16 Sep 2026.

Read full publication at:
Please sign in to see all details.

Stats

1-terrible, 9-excellent. How would you rate this publication? Sign in in to submit your rating.

Post a comment

You need to be signed in to post comments. You can sign in here.

Comments

There are no comments yet.