已入深夜,您辛苦了!由于当前在线用户较少,发布求助请尽量完整地填写文献信息,科研通机器人24小时在线,伴您度过漫漫科研夜!祝你早点完成任务,早点休息,好梦!

Self-Trained Target Detection of Radar and Sonar Images Using Automatic Deep Learning

计算机科学 人工智能 雷达成像 自动目标识别 雷达 遥感 雷达锁定 合成孔径雷达 声纳 计算机视觉 地质学 连续波雷达 电信
作者
Peng Zhang,Jinsong Tang,Heping Zhong,Mingqiang Ning,Dandan Liu,Ke Wu
出处
期刊:IEEE Transactions on Geoscience and Remote Sensing [Institute of Electrical and Electronics Engineers]
卷期号:60: 1-14 被引量:102
标识
DOI:10.1109/tgrs.2021.3096011
摘要

Recent deep learning (DL) detectors adopted by radar or sonar (RS) are normally trained with transfer learning, where the typical workflow is to pretrain a convolutional neural network (CNN) on external large-scale classification datasets (e.g., ImageNet) as the backbone and then finetune the entire detector on detection datasets. Though transfer learning could effectively avoid overfitting, transferred models are usually redundant and might not generalize well on RS datasets. To achieve high generalization and to eliminate the dependence on transfer learning, a self-trained target detection method is established by including Automatic Deep Learning (AutoDL) to design optimal detectors. This self-trained target detection consists of three stages. First, a derived classification dataset (DCD) consisting of image blocks of targets and backgrounds is derived from detection datasets. Then, a memory-efficient Differentiable Architecture Search algorithm with flexible search space and large inputs (FL-DARTS), which is characterized by its predefined multistride convolutions, poolings, and unique super-structure, is proposed to automatically design and self-train optimal CNNs on DCDs. Finally, self-trained AutoDL detectors are implemented with the automatic backbone designed by FL-DARTS. We evaluated three self-trained AutoDL detectors on the public SAR ship detection dataset (SSDD) and the self-made sonar common target detection dataset (SCTD). The experiments show that while the number of parameters of automatic backbones designed for SSDD and SCTD are only 11.8% and 15.2% of that of ResNet50, self-trained AutoDL detectors implemented with automatic backbones significantly outperform their transfer learning detectors and achieve state-of-the-art detection precisions and high detection speeds. Data, codes are publicly available.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
七听发布了新的文献求助20
1秒前
纯真如南发布了新的文献求助10
1秒前
1秒前
zrssovereign完成签到 ,获得积分10
2秒前
聪明平灵完成签到 ,获得积分10
2秒前
奋斗的桐完成签到,获得积分10
2秒前
peanuttt发布了新的文献求助20
2秒前
李锦奥发布了新的文献求助10
3秒前
3秒前
4秒前
6秒前
7秒前
7秒前
花生王子完成签到 ,获得积分10
8秒前
理想完成签到 ,获得积分10
8秒前
null的应助被ysy采纳,获得10
9秒前
10秒前
脑洞疼的应助被Dai采纳,获得10
10秒前
毛日骏发布了新的文献求助10
10秒前
初景的应助被牛马之采纳,获得20
11秒前
seasona发布了新的文献求助10
12秒前
科研通AI2S的应助被勤奋笑卉采纳,获得10
13秒前
Lov完成签到 ,获得积分10
14秒前
EmeraldFlamel完成签到 ,获得积分10
14秒前
15秒前
15秒前
不做科研发布了新的文献求助10
15秒前
Xtay完成签到 ,获得积分10
17秒前
18秒前
19秒前
alwry完成签到,获得积分10
19秒前
quan完成签到,获得积分10
19秒前
车车发布了新的文献求助10
20秒前
科研通AI6.4的应助被咎如天采纳,获得10
22秒前
琳琅完成签到,获得积分10
23秒前
23秒前
王泉林发布了新的文献求助10
24秒前
可爱的函函的应助被李锦奥采纳,获得10
25秒前
25秒前
磊少完成签到,获得积分10
25秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
八旗制度の研究 600
Hidden Empire of Finance: How Wall Street Profits from Our Cities and Fuels Global Inequality 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8165576
求助须知:如何正确求助?哪些是违规求助? 9559107
关于积分的说明 21748964
捐赠科研通 7756283
什么是DOI,文献DOI怎么找? 3428926
关于科研通互助平台的介绍 2553233
邀请新用户注册赠送积分活动 2473520