DenoDet：作为可变形多子空间特征去噪的注意力机制用于SAR图像目标检测
DenoDet: Attention as Deformable Multi-Subspace Feature Denoising for Target Detection in SAR Images
AI总结：
针对SAR图像散斑噪声和微小模糊目标检测难题，提出结合频域变换的DenoDet网络及动态注意力模块TransDeno、可变形组全连接层，在多数据集上实现SOTA检测效果。
摘要：
合成孔径雷达（SAR）目标检测长期受固有散斑噪声以及大量微小、模糊目标的制约。尽管深度神经网络已推动SAR目标检测取得进展，但其固有的低频偏差和训练后静态权重在相干噪声下表现不佳，且难以在异质地貌中保留细微细节。受传统SAR图像去噪方法启发，我们提出DenoDet网络，该网络借助显式频域变换校准卷积偏差，更多关注高频信息，形成自然的多尺度子空间表示，从多子空间去噪的角度进行目标检测。我们设计了TransDeno这一动态频域注意力模块，其作用相当于变换域软阈值操作，通过保留显著目标信号并衰减噪声，实现跨子空间的动态去噪。为自适应调整子空间处理粒度，我们还提出可变形组全连接层（DeGroFC），可根据输入特征动态改变分组。无需额外技巧，我们的即插即用式TransDeno在多个SAR目标检测数据集上取得了最优成绩。代码可在https://github.com/GrokCV/GrokSAR获取。
英文摘要：
Synthetic Aperture Radar (SAR) target detection has long been impeded by inherent speckle noise and the prevalence of diminutive, ambiguous targets. While deep neural networks have advanced SAR target detection, their intrinsic low-frequency bias and static post-training weights falter with coherent noise and preserving subtle details across heterogeneous terrains. Motivated by traditional SAR image denoising, we propose DenoDet, a network aided by explicit frequency domain transform to calibrate convolutional biases and pay more attention to high-frequencies, forming a natural multi-scale subspace representation to detect targets from the perspective of multi-subspace denoising. We design TransDeno, a dynamic frequency domain attention module that performs as a transform domain soft thresholding operation, dynamically denoising across subspaces by preserving salient target signals and attenuating noise. To adaptively adjust the granularity of subspace processing, we also propose a deformable group fully-connected layer (DeGroFC) that dynamically varies the group conditioned on the input features. Without bells and whistles, our plug-and-play TransDeno sets state-of-the-art scores on multiple SAR target detection datasets. The code is available at https://github.com/GrokCV/GrokSAR.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
