arrow
返回

Plane Net: an efficient local feature extraction network

delete2021-12-07
delete3
delete
OA
AI
B
Bin Lin
H
Houcheng Su
D
Danyang Li
A
Ao Feng
H
Hongxiang Li
J
Jiao Li
K
Kailin Jiang
姜红波 封面图
姜红波 (Hongbo Jiang)
X
Xinyao Gong
T
Tao Liu *
DOI:10.7717/peerj-cs.783delete
delete原文链接
delete分享
delete收藏
查看原文
摘要

摘要

En 中文
Due to memory and computing resources limitations, deploying convolutional neural networks on embedded and mobile devices is challenging. However, the redundant use of the 1 x 1 convolution in traditional light-weight networks, such as MobileNetV1, has increased the computing time. By utilizing the 1 x 1 convolution that plays a vital role in extracting local features more effectively, a new lightweight network, named PlaneNet, is introduced. PlaneNet can improve the accuracy and reduce the numbers of parameters and multiply-accumulate operations (Madds). Our model is evaluated on classification and semantic segmentation tasks. In the classification tasks, the CIFAR-10, Caltech-101, and ImageNet2012 datasets are used. In the semantic segmentation task, PlaneNet is tested on the VOC2012 datasets. The experimental results demonstrate that PlaneNet (74.48%) can obtain higher accuracy than MobileNetV3-Large (73.99%) and GhostNet (72.87%) and achieves state-of-the-art performance with fewer network parameters in both tasks. In addition, compared with the existing models, it has reached the practical application level on mobile devices. The code of PlaneNet on GitHub:https://github.om/LinB203/Planenet.
Keyword:
Feature extraction
Local feature fusion
efficiency
Strong operability
Reduce redundant
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

PeerJ Computer Science 封面图
PeerJ Computer Science
IF:
2.5
论文数:
3.4K
被引数:
6.9K

机构

S
Sichuan Agricultural University
学者数:
2.3W
论文数: 9.5K
被引数: 1.4W
引用论文

引用论文

METASPACE: A community-populated knowledge base of spatial metabolomes in health and disease
err
IF0
err2019-02-03
err0
errOAAI
errTheodore Alexandrov; Katja Ovchinnikova; Andrew Palmer; Vitaly Kovalev; Artem Tarasov; Lachlan Stuart; Renat Nigmetzianov; Dominik Fay; Mathieu Gaudin; Cristina Gonzalez Lopez; Marina Vetter; John Swales; Mark Bokhart; Mario Kompauer; James McKenzie; Luca Rappez; Dusan Velickovic; Regis Lavigne; Guanshi Zhang; Dinaiz Thinagaran; Elisa Ruhland; Marta Sans; Sergio Triana; Denis Abu Sammour; Sarah Aboulmagd; Charlotte Bagger; Nicole Strittmatter; Angelos Rigopoulos; Erin Gemperline; Asta Maria Joensen; Benedikt Geier; Christine Quiason; Eric Weaver; Mridula Prasad; Benjamin Balluff; Konstantin Nagornov; Lingjun Li; Michael Linscheid; Carsten Hopf; Dimitri Heintz; Manuel Liebeke; Bernhard Spengler; Berin Boughton; Christian Janfelt; Kumar Sharma; Charles Pineau; Christopher Anderton; Shane Ellis; Michael Becker; József Pánczél; Georges Da Violante; David Muddiman; Richard Goodwin; Livia Eberlin; Zoltan Takats; Sheerin Shahidi-Latham
err分享
err收藏
ImageNet Large Scale Visual Recognition ChallengeImageNet大规模视觉识别挑战
err2015-04-11
err2.7W
PREAI
errRussakovsky, Olga; Deng, Jia; Su, Hao; Krause, Jonathan; Satheesh, Sanjeev; Ma, Sean; Huang, Zhiheng; Karpathy, Andrej; Khosla, Aditya; Bernstein, Michael; Berg, Alexander C.; Fei-Fei, Li
err分享
err收藏
The PASCAL Visual Object Classes Challenge: A RetrospectivePASCAL视觉对象课程挑战: 回顾性
err2014-06-25
err5.0K
PREAI
errEveringham, Mark; Eslami, S. M. Ali; Van Gool, Luc; Williams, Christopher K. I.; Winn, John; Zisserman, Andrew
err分享
err收藏
学者 查看更多内容