计算机应用与软件2025，Vol.42Issue(5)：255-262,281,9.DOI:10.3969/j.issn.1000-386x.2025.05.035
基于剪枝的SAR图像舰船目标检测模型压缩方案
COMPRESSION SCHEME OF SAR IMAGES SHIP TARGET DETECTION MODEL BASED ON PRUNING
摘要
Abstract
The resources of edge devices are limited,but the deep neural network model is large and has many parameters.Aimed at the difficulty of deploying the SAR image ship target detection model based on deep neural network on edge devices,a compression scheme based on pruning is proposed to lightweight the YOLOv3-SPP model.Experiments were performed on AIR-SARSHIP-1.0 data set using this method.Experimental results show that the original model can be compressed to less than 10％by the proposed compression scheme,while the speed is increased by 1.5 times and the accuracy is only slightly decreased by 0.02,which greatly reduces the difficulty of deploying the model at the edge and breaks through the limitations of hardware resources.关键词
合成孔径雷达/舰船目标检测/压缩/过滤器剪枝/层剪枝/蒸馏Key words
Synthetic aperture radar/Ship target detection/Compression/Filter pruning/Layer pruning/Distillation分类
信息技术与安全科学引用本文复制引用
李卓阳,郭荣佐,车思韬,杨军..基于剪枝的SAR图像舰船目标检测模型压缩方案[J].计算机应用与软件,2025,42(5):255-262,281,9.基金项目
国家自然科学基金项目(11905153,61701331). （11905153,61701331）
