| 特征图知识蒸馏引导的轻量化任意方向SAR舰船目标检测器 |
| |
| 引用本文： | 陈诗琪,王威,占荣辉,张军,刘盛启.特征图知识蒸馏引导的轻量化任意方向SAR舰船目标检测器[J].雷达学报,2023,12(1):140-153. |
| |
| 作者姓名： | 陈诗琪 王威 占荣辉 张军 刘盛启 |
| |
| 作者单位： | 国防科技大学自动目标识别重点实验室 长沙 410073 |
| |
| 基金项目： | 国家自然科学基金(61901500)，湖南省科技创新计划(2020RC2044)，中国博士后科学基金(2020TQ0082) |
| |
| 摘 要： | 基于有向边界框的合成孔径雷达(SAR)舰船目标检测器能输出精准的边界框，但仍存在模型计算复杂度高、推理速度慢、存储消耗大等问题，导致其难以在星载平台上部署。基于此该文提出了结合特征图和检测头分支知识蒸馏的无锚框轻量化旋转检测方法。首先，结合目标的长宽比和方向角信息提出改进高斯核，使生成的热度图能更好地刻画目标形状。然后在检测器预测头部引入前景区域增强分支，使网络更关注前景特征且抑制背景杂波的干扰。在训练轻量化网络时，将像素点间的相似度构建为热度图蒸馏知识。为解决特征蒸馏中正负样本不平衡问题，将前景注意力区域作为掩模引导网络蒸馏与目标相关的特征。另外，该文提出全局语义模块对像素进行上下文信息建模，能够结合背景知识加强目标精确表征。基于HRSID数据集的实验结果表明所提方法在模型参数仅有9.07 M的轻量化条件下，mAP能达到80.71%，且检测帧率满足实时应用需求。
|
| 关 键 词： | 合成孔径雷达舰船目标检测 轻量化旋转框检测 改进高斯核 前景区域增强 知识蒸馏 |
| 收稿时间： | 2021-12-25 |
A Lightweight,Arbitrary-oriented SAR Ship Detector via Feature Map-based Knowledge Distillation |
| |
| CHEN Shiqi,WANG Wei,ZHAN Ronghui,ZHANG Jun,LIU Shengqi.A Lightweight,Arbitrary-oriented SAR Ship Detector via Feature Map-based Knowledge Distillation[J].Journal of Radars,2023,12(1):140-153. |
| |
| Authors: | CHEN Shiqi WANG Wei ZHAN Ronghui ZHANG Jun LIU Shengqi |
| |
| Affiliation: | National Key Laboratory of Science and Technology on Automatic Target Recognition, National University of Defense Technology, Changsha 410073, China |
| |
| Abstract: | In the Synthetic Aperture Radar (SAR) ship target detection task, the targets have a large aspect ratio and dense distribution, and they are arranged in arbitrary directions. The oriented bounding box-based detection methods can output accurate detection results. However, these methods are strongly restricted by high computational complexity, slow inference speed, and large storage consumption, which complicate their deployment on space-borne platforms. To solve the above issues, a lightweight oriented anchor-free-based detection method is proposed by combining feature map and prediction head knowledge distillation. First, we propose an improved Gaussian kernel based on the aspect ratio and angle information so that the generated heatmaps can better describe the shape of the targets. Second, the foreground region enhancement branch is introduced to make the network focus more on foreground features while suppressing the background interference. When training the lightweight student network, the similarity between pixels is treated as transferred knowledge in heatmap distillation. To tackle the imbalance between positive and negative samples in feature distillation, the foreground attention region is applied as a mask to guide the feature distillation process. In addition, a global semantic module is proposed to model the contextual information around pixels, and the background knowledge is combined to further strengthen the feature representation. Experimental results based on HRSID show that our method can achieve 80.71% mAP with only 9.07 M model parameters, and the detection frame rate meets the needs of real-time applications. |
| |
| Keywords: | |
|
| 点击此处可从《雷达学报》浏览原始摘要信息 |
|
点击此处可从《雷达学报》下载全文 |
|
