Due to Synthetic Aperture Radar (SAR) imaging characteristics, SAR vehicle
recognition faces the problem of extracting discriminative and robust target
features from a small dataset. Deep learning has shown impressive performance
on the MSTAR dataset. However, data bias in a small dataset, such as background
correlation, impairs the causality of these methods, i.e., discriminative
features contain target and background differences. Moreover, different
operating conditions of SAR lead to target signatures and background clutter
variations in imaging results. However, many deep learning-based methods only
verify robustness to target or background variations in the current
experimental setting. In this paper, we propose a novel domain alignment
framework named Hierarchical Disentanglement-Alignment Network (HDANet) to
enhance features' causality and robustness. Concisely, HDANet consists of three
parts: The first part uses data augmentation to generate signature variations
for domain alignment. The second part disentangles the target features through
a multitask-assisted mask to prevent non-causal clutter from interfering with
subsequent alignment and recognition. Thirdly, a contrastive loss is employed
for domain alignment to extract robust target features, and the SimSiam
structure is applied to mitigate conflicts between contrastive loss and feature
discrimination. Finally, the proposed method shows high robustness across
MSTAR's multiple target, sensor, and environment variants. Noteworthy, we add a
new scene variant to verify the robustness to target and background variations.
Moreover, the saliency map and Shapley value qualitatively and quantitatively
demonstrate causality. Our code is available in
https://github.com/waterdisappear/SAR-ATR-HDANet.

本文提出了一种新颖的 Hierarchical Disentanglement-Alignment Network（HDANet）方法，通过数据对齐框架增强了特征的因果性和鲁棒性，展现了在多种 SAR 的目标和环境变量中的高鲁棒性。

用于强健 SAR 车辆识别的分层去纠缠网络

Hierarchical Disentanglement-Alignment Network for Robust SAR Vehicle  Recognition

In recent years, deep learning has been widely used in SAR ATR and achieved
excellent performance on the MSTAR dataset. However, due to constrained imaging
conditions, MSTAR has data biases such as background correlation, i.e.,
background clutter properties have a spurious correlation with target classes.
Deep learning can overfit clutter to reduce training errors. Therefore, the
degree of overfitting for clutter reflects the non-causality of deep learning
in SAR ATR. Existing methods only qualitatively analyze this phenomenon. In
this paper, we quantify the contributions of different regions to target
recognition based on the Shapley value. The Shapley value of clutter measures
the degree of overfitting. Moreover, we explain how data bias and model bias
contribute to non-causality. Concisely, data bias leads to comparable
signal-to-clutter ratios and clutter textures in training and test sets. And
various model structures have different degrees of overfitting for these
biases. The experimental results of various models under standard operating
conditions on the MSTAR dataset support our conclusions. Our code is available
at this https URL

该研究使用 Shapley 值量化不同区域对目标识别的贡献，发现深度学习在 SAR ATR 中对于杂波的过拟合程度反映了其非因果性，并解释了数据偏差和模型偏差对非因果性的影响。