数字农科院2.0

Lightweight Network Ensemble Architecture for Environmental Perception on the Autonomous System

文献类型： 外文期刊

作者： Dai Y.; Wang J.; Li J.; Meng L.; Wang S.

作者机构：

关键词： Network architecture; Parallel architectures; Semantic Segmentation; Semantic Web; Component networks; Ensemble networks; Environmental information; Environmental perceptions; Generalization ability; High-accuracy; Network ensemble; Neural network's ensemble; Real-time application; Semantic segmentation; Semantics

期刊名称： CMES - Computer Modeling in Engineering and Sciences

ISSN： 1526-1492

年卷期： 2023 年 134 卷 1 期

页码：

收录情况： SCIE（2023版） ; ; EI（2023版）

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. © 2023 Tech Science Press. All rights reserved.

分类号：

  • 相关文献

[1]Improving Segmentation Accuracy For Ears Of Winter Wheat At Flowering Stage By Semantic Segmentation. Ma, JC, Li, YX, Liu, HJ, Du, KM, Zheng, FX, Wu, YF, Zhang, LX. 2020

作者其他论文 更多>>