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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Wang, Chenwei, Xu, Renjie, Wu, Congwen, Yin, Cunyi, Liao, Ziyun, Mao, Deqing, Zhang, Sitong, Yan, Hong
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908403981352960
author Wang, Chenwei
Xu, Renjie
Wu, Congwen
Yin, Cunyi
Liao, Ziyun
Mao, Deqing
Zhang, Sitong
Yan, Hong
author_facet Wang, Chenwei
Xu, Renjie
Wu, Congwen
Yin, Cunyi
Liao, Ziyun
Mao, Deqing
Zhang, Sitong
Yan, Hong
contents 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 $λ_w$, forming the reasoning logic $\sum_{i} {{r_b^i} \times {λ_w^i}} =pred$ 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_09377
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle An Interpretable Two-Stage Feature Decomposition Method for Deep Learning-based SAR ATR
Wang, Chenwei
Xu, Renjie
Wu, Congwen
Yin, Cunyi
Liao, Ziyun
Mao, Deqing
Zhang, Sitong
Yan, Hong
Image and Video Processing
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 $λ_w$, forming the reasoning logic $\sum_{i} {{r_b^i} \times {λ_w^i}} =pred$ 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.
title An Interpretable Two-Stage Feature Decomposition Method for Deep Learning-based SAR ATR
topic Image and Video Processing
url https://arxiv.org/abs/2506.09377