arXiv：cs.AI· Yansong Lin, Zihan Cheng, Ziyue Yang, Xinming Wang, Jielei Wang, Guoming Lu, Zongyong Cui·· 6 小时前AI 评分29
FSCE：面向抗噪 SAR ATR 的目标感知频率-空间协同增强框架
FSCE: A Target-Aware Frequency-Spatial Collaborative Enhancement Framework for Noise-Resilient SAR ATR
AI 导读
研究者提出 FSCE 框架用于抗噪 SAR ATR，通过频率-空间协同建模实现早期特征稳定并结合语义正则化。该框架在网络入口设计 FS-EAE 模块抑制噪声传播，并引入 APSA 机制以在线教师策略施加语义约束。在 MSTAR、OpenSARShip 和 FUSARShip 上验证有效，轻量版 FSCE-Net_μ 仅 0.17M 参数，已被 IEEE TCSVT 接收。
正文
Abstract:Synthetic aperture radar automatic target recognition (SAR ATR) is severely challenged by coherent speckle noise, whose interference can be progressively amplified by hierarchical nonlinear transformations and eventually damage high-level semantic representations. To address this issue, we propose a Target-Aware Frequency-Spatial Collaborative Enhancement (FSCE) framework for noise-resilient SAR ATR, which integrates frequency-spatial modeling for early feature stabilization with semantic regularization. Specifically, we design a Frequency-Spatial Early-stage Adaptive Enhancement (FS-EAE) module at the network entrance to suppress noise propagation and preserve target structures through collaborative spatial-frequency modeling. Building upon stabilized shallow representation, we further introduce an Adaptive Policy-driven Semantic Alignment (APSA) mechanism, which uses an online teacher policy to impose top-down semantic constraints on the student and feeds semantic guidance back to the enhanced early features during training. Experiments on MSTAR, OpenSARShip, and FUSARShip demonstrate the effectiveness of this synergy. Moreover, the competitive performance of our lightweight impletation $\text{FSCE-Net}_\mu$ with only 0.17M parameters suggests that the proposed framework is applicable to both high-capacity and lightweight architectures.
| Comments: | Accepted by IEEE Transactions on Circuits and Systems for Video Technology (TCSVT) |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2603.21565 [cs.CV] |
| (or arXiv:2603.21565v3 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2603.21565 arXiv-issued DOI via DataCite |
|
| Journal reference: | IEEE Transactions on Circuits and Systems for Video Technology, Early Access, 2026 |
| Related DOI: | https://doi.org/10.1109/TCSVT.2026.3737445
DOI(s) linking to related resources |
Submission history
From: Yansong Lin [view email]
[v1]
Mon, 23 Mar 2026 04:35:31 UTC (4,024 KB)
[v2]
Wed, 23 Sep 2026 08:23:38 UTC (14,879 KB)
[v3]
Tue, 6 Oct 2026 05:30:22 UTC (14,879 KB)
来源：arXiv：cs.AI · arxiv.org