二维码(扫一下试试看!) | 一种元卷积网络和持续学习融合的洞库类目标识别方法 | Cave Targets Recognition on Meta-Convolutional Networks and Lifelong Learning | 投稿时间:2019-05-13 | DOI:10.15918/j.tbit1001-0645.2019.148 | 中文关键词:洞库类目标目标识别深度卷积网络元学习持续学习 | English Keywords:cave targettarget recognitiondeep convolutional networksmeta-learninglifelong learning | 基金项目:国家科技支撑计划资助项目(2015BAK04B02) | | 摘要点击次数:991 | 全文下载次数:343 | 中文摘要: | 洞库类目标是高价值识别目标,针对洞库类目标样本数据难以获得、样本内部数据相似度较高、人工设计识别特征方法局限性较大、普通深度网络需要海量数据等问题,提出了结合元学习和深度卷积网络的元-卷积网络(MCNN),并融合持续学习理论的洞库类目标识别方法(MCNN-LLS).首先结合深度卷积网络、元学习的理论建立元-卷积网络,该网络可利用旧知识指导新知识的训练,利用小样本数据即可训练得到识别能力较高的深度洞库模型;然后融合持续学习理论,建立持续学习系统(LLS),设计专家审核模型判别深度洞库模型的识别结果,并引入潜在任务、模型异步更新等方法,达到模型持续学习、持续更新的效果.实验表明,本文方法所需样本数量少,对洞库类目标识别准确率高,且识别能力可随识别过程中新数据的积累逐步提高. | English Summary: | Cave target is the high-value recognizing target. According to the difficulty about cave target data collection, the high data similarity, the limitation of the artificial feature, and the deep neural networks needs massive data, a method of combining meta-convolutional network and deep convolutional networks named meta-convolutional networks(MCNN), and combining lifelong learning was proposed (MCNN-LLS). Firstly, a meta-convolutional network was established by combining deep convolutional network and meta-learning. This network can use old knowledge to guide the training process, and can use the small sample to train an ideal cave detection model. Then combining lifelong learning and establishing the lifelong learning system (LLS), designing the expert review model to identify the recognition results by the cave detection model, and introducing potential tasks, model asynchronously update to reach the effect of model sustainable updating. Experiments show that this method only needs small sample, has high accuracy of recognizing cave target, and the recognition effect can gradually increase with the accumulation of new data. | 查看全文查看/发表评论下载PDF阅读器 | |
王懿,张爱霞,郭瑞岩,张成良.六自由度水下机械臂动力学模型及流阻影响研究[J].北京理工大学学报(自然科学版),2020,40(11):1143~1149.WANGYi,ZHANGAi-xia,GUORui-yan,ZHANGCheng-liang.DynamicModelof6-DOFUnderw ... 北京理工大学科研学术 本站小编 Free考研考试 2021-12-21.北京理工大学学报2020年总目次(第40卷)[J].北京理工大学学报(自然科学版),2020,40(12):1369~1386..[J].TransactionsofBeijingInstituteofTechnology,2020,40(12):1369-1386.二维码(扫一下试试看!)北京理 ... 北京理工大学科研学术 本站小编 Free考研考试 2021-12-21陈越洋,何行宽,李晨瑶.基于Retinex理论的电子内镜图像增强算法[J].北京理工大学学报(自然科学版),2021,41(9):985~989.CHENYueyang,HEXingkuan,LIChenyao.EndoscopicImageEnhancementBasedonRetinexTheo ... 北京理工大学科研学术 本站小编 Free考研考试 2021-12-21张江霄,冯春辉,马金鑫,张斌,徐畅,李舟军,党莹.可任意花费的可传递电子现金系统[J].北京理工大学学报(自然科学版),2019,39(3):283~289.ZHANGJiang-xiao,FENGChun-hui,MAJin-xin,ZHANGBin,XUChang,LIZhou-jun,DANG ... 北京理工大学科研学术 本站小编 Free考研考试 2021-12-21江维,王杰,陈伟,余联庆,李红军,吴功平.半结构环境中电力作业机器人机械手鲁棒轨迹跟踪控制[J].北京理工大学学报(自然科学版),2019,39(4):391~398.JIANGWei,WANGJie,CHENWei,YULian-qing,LIHong-jun,WUGong-ping.Manipu ... 北京理工大学科研学术 本站小编 Free考研考试 2021-12-21江维,周志远,陈伟,余联庆,李红军,吴功平.高压电缆移动作业机器人机械手双闭环自主定位控制[J].北京理工大学学报(自然科学版),2019,39(6):589~596.JIANGWei,ZHOUZhi-yuan,CHENWei,YULian-qing,LIHong-jun,WUGong-Ping.M ... 北京理工大学科研学术 本站小编 Free考研考试 2021-12-21严保康,周凤星,徐波.基于GST的变速机械故障信号稀疏特征提取方法[J].北京理工大学学报(自然科学版),2019,39(6):603~608.YANBao-kang,ZHOUFeng-xing,XUBo.SparseFeatureExtractionforVariableSpeedMachiner ... 北京理工大学科研学术 本站小编 Free考研考试 2021-12-21姚国伟,张凤,曹建文,邓志均.基于有向图的运载火箭综合电子系统设计方法[J].北京理工大学学报(自然科学版),2019,39(6):650~654.YAOGuo-wei,ZHANGFeng,CAOJian-wen,DENGZhi-jun.LaunchVehicleIntegratedElectron ... 北京理工大学科研学术 本站小编 Free考研考试 2021-12-21吴鹏,孟祥远,王子晔,高建伟.基于神经动力学的冗余机械臂恒定转速比算法[J].北京理工大学学报(自然科学版),2019,39(10):1081~1085.WUPeng,MENGXiang-yuan,WANGZi-ye,GAOJian-wei.ConstantRotationRatioofRedund ... 北京理工大学科研学术 本站小编 Free考研考试 2021-12-21.北京理工大学学报2019年总目次(第39卷)[J].北京理工大学学报(自然科学版),2019,39(12):1321~1338..[J].TransactionsofBeijingInstituteofTechnology,2019,39(12):1321-1338.二维码(扫一下试试看!)北京理 ... 北京理工大学科研学术 本站小编 Free考研考试 2021-12-21
| |