Detection tasks based on Synthetic aperture radar (SAR) images have been studied widely but severely constrained by the quality of datasets. Meanwhile, both the unperceived category imbalance problem and SAR image discrepancy of multi-class SAR datasets are not fully considered. Researchers usually care about the foreground-background imbalance more than the class imbalance for SAR images. To solve these problems, an entropy-based re-sampling method is proposed in which category imbalance and quality discrepancies of SAR images are both considered. Initially, the relationship is established between variance-weighted image entropy and factors affecting SAR image quality, such as noise, resolution, and density, thereby validating entropy as a robust metric for image quality assessment. Subsequently, quantity penalty scores of categories and difficulty penalty scores of each image are calculated separately to capture the inter-class and intra-class disparities. Next, logarithmic smoothing is employed to avoid overestimation of image difficulty due to the margin effect. Finally, all these scores are combined to generate normalized scores representing the final distribution of the dataset to guide the training process. The proposed approach serves as a plug-and-play strategy for general SAR detection tasks, and experimental results indicate a significant performance improvement. Specifically, detection accuracy in terms of AP for airplanes and bridges (minority classes) in the MSAR dataset is improved by 16.6 % and 13.0 %, respectively, compared to the YOLOv5 baseline, with only a minimal 1.6 % sacrifice in ship detection (majority class). The datasets and the codes can be found at https://www.radars.ac.cn/web/data/getData?dataType=MSAR, https://github.com/Phoenix0qi/Yolov5-entropy-balance/tree/master.

中文翻译：

---

基于熵的SAR类不平衡目标重采样方法

基于合成孔径雷达（SAR）图像的检测任务已被广泛研究，但受到数据集质量的严重限制。同时，没有充分考虑未感知的类别不平衡问题和多类SAR数据集的SAR图像差异。对于 SAR 图像，研究人员通常更关心前景-背景不平衡，而不是类不平衡。为了解决这些问题，提出了一种同时考虑SAR图像类别不平衡和质量差异的基于熵的重采样方法。首先，在方差加权图像熵和影响SAR图像质量的因素（例如噪声、分辨率和密度）之间建立关系，从而验证熵作为图像质量评估的鲁棒度量。随后，分别计算类别的数量惩罚分数和每个图像的难度惩罚分数，以捕获类间和类内的差异。接下来，采用对数平滑来避免由于边缘效应而高估图像难度。最后，将所有这些分数组合起来生成代表数据集最终分布的归一化分数，以指导训练过程。所提出的方法可作为一般 SAR 检测任务的即插即用策略，实验结果表明性能显着提高。具体而言，与 YOLOv5 基线相比，MSAR 数据集中飞机和桥梁（少数类）的 AP 检测精度分别提高了 16.6% 和 13.0%，而船舶检测（少数类）仅损失了 1.6% ）。数据集和代码可以在https://www.radars.ac.cn/web/data/getData?dataType=MSAR、https://github.com/Phoenix0qi/Yolov5-entropy-balance/tree/master找到。