维普中文期刊产品整合服务

Lightweight Network Ensemble Architecture for Environmental Perception on the Autonomous System

查看全文 作　　者：Yingpeng [1]Dai;Junzheng [1]Wang;Jing [1]Li;Lingfeng [2]Meng;Songfeng [2]Wang 高影响力作者 机构地区：[1]School of Automation,Beijing Institute of Technology,Beijing,100081,China;[2]Institute of Tobacco Research of CAAS,Qingdao,266000,China高影响力机构 出　　处：《Computer Modeling in Engineering & Sciences》索引2023年第1期,共22页高影响力期刊 基　　金：supported by the National Key Research and Development Program of China under Grant 2019YFC1511401;the National Natural Science Foundation of China under Grant 62173038 and 61103157;Science Foundation for Young Scholars of Tobacco Research Institute of Chinese Academy of Agricultural Sciences under Grant 2021B05;Key Scientific and Tech-nological Research and Development Project of China National Tobacco Corporation under Grant 110202102007. 摘　　要：It is important for the autonomous system to understand environmental information.For the autonomous system,it is desirable to have a strong generalization ability to deal with different complex environmental information,as well as have high accuracy and quick inference speed.Network ensemble architecture is a good choice to improve network performance.However,it is unsuitable for real-time applications on the autonomous system.To tackle this problem,a new neural network ensemble named partial-shared ensemble network(PSENet)is presented.PSENet changes network ensemble architecture from parallel architecture to scatter architecture and merges multiple component networks together to accelerate the inference speed.To make component networks independent of each other,a training method is designed to train the network ensemble architecture.Experiments on Camvid and CIFAR-10 reveal that PSENet achieves quick inference speed while maintaining the ability of ensemble learning.In the real world,PSENet is deployed on the unmanned system and deals with vision tasks such as semantic segmentation and environmental prediction in different fields. 关 键 词：Neural network ensemble real-time application CLASSIFICATION semantic segmentation
相关文献

参考文献(52)

耦合文献(5)

网站首页 | 关于我们 | 联系我们 | 产品服务 | 客服中心 | 广告服务 | 版权声明 | 网站联盟 | 友情链接 | 售卡网点

版权所有© 渝B2-20050021-1　渝公网安备 50019002500403号　违法和不良信息举报中心

互联网出版许可证 新出网证(渝)字10号 全国400电话 - 免长途话费