A New Light Weight Convolutional Neural Network for Mobile Devices

被引：0
|
作者：
Lai, Kuan-Ting [1 ]
Lin, Guo-Shiang [1 ]
机构：
[1] Natl Chin Yi Univ Technol, Dept Comp Sci & Informat Engn, Taichung, Taiwan
来源：
2022 IEEE INTERNATIONAL CONFERENCE ON CONSUMER ELECTRONICS - TAIWAN, IEEE ICCE-TW 2022 | 2022年
关键词：
convolution neural network; Deep learning; Mobilenet;
D O I：
10.1109/ICCE-TAIWAN55306.2022.9869273
中图分类号：
TP39 [计算机的应用];
学科分类号：
081203 ; 0835 ;
摘要：
In this paper, we propose a light-weight convolutional neural network based on depth-wise separable convolutions and cross stage partial (CSP) network. Dissimilar to MobileNetV3, the proposed network is composed of some CSP blocks to reduce the model size and computational operations. For performance evaluation, Cifar10 and Cifar100 are used for testing. Compared to MobileNetv3, the model size and execution time of the proposed network in PC and mobile device are smaller. Therefore, the experimental results show that the proposed light-weight network can effectively extract visual features for image classification compared with MobileNetV3.
引用
收藏
页码：349 / 350
页数：2
相关论文
共 50 条
  • [1] Deep Convolutional Neural Network on iOS Mobile Devices
    Chen, Chun-Fu
    Lee, Gwo Giun
    Sritapan, Vincent
    Lin, Ching-Yung
    2016 IEEE INTERNATIONAL WORKSHOP ON SIGNAL PROCESSING SYSTEMS (SIPS), 2016, : 130 - 135
  • [2] ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
    Zhang, Xiangyu
    Zhou, Xinyu
    Lin, Mengxiao
    Sun, Ran
    2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, : 6848 - 6856
  • [3] Using Convolutional Neural Network for Image hnhancement on Mobile Devices
    Despotovici, Mihai
    Mocanu, Irina
    Lucia, Rusu
    2019 IEEE 15TH INTERNATIONAL CONFERENCE ON INTELLIGENT COMPUTER COMMUNICATION AND PROCESSING (ICCP 2019), 2019, : 359 - 364
  • [4] Light-weight Visual Place Recognition Using Convolutional Neural Network for Mobile Robots
    Park, Chanjong
    Jang, Junik
    Zhang, Lei
    Jung, Jae-Il
    2018 IEEE INTERNATIONAL CONFERENCE ON CONSUMER ELECTRONICS (ICCE), 2018,
  • [5] MobiVSR : Efficient and Light-weight Neural Network for Visual Speech Recognition on Mobile Devices
    Shrivastava, Nilay
    Saxena, Astitwa
    Kumar, Yaman
    Shah, Rajiv Ratn
    Stent, Amanda
    Mahata, Debanjan
    Kaur, Preeti
    Zimmermann, Roger
    INTERSPEECH 2019, 2019, : 2753 - 2757
  • [6] Review of Optimal Convolutional Neural Network Accelerator Platforms for Mobile Devices
    Kim H.
    Journal of Computing Science and Engineering, 2022, 16 (02) : 113 - 119
  • [7] Wireless Devices Identification with Light-Weight Convolutional Neural Network Operating on Quadrant IQ Transition Image
    Tamura, Hiro
    Yanagisawa, Kiyoshi
    Shirane, Atsushi
    Okada, Kenichi
    2020 18TH IEEE INTERNATIONAL NEW CIRCUITS AND SYSTEMS CONFERENCE (NEWCAS'20), 2020, : 106 - 109
  • [8] Convolutional Neural Network-Based Technique for Gaze Estimation on Mobile Devices
    Akinyelu, Andronicus A.
    Blignaut, Pieter
    FRONTIERS IN ARTIFICIAL INTELLIGENCE, 2022, 4
  • [9] Light-weight Convolutional Neural Network for Distracted Driver Classification
    Duy-Linh Nguyen
    Putro, Muhamad Dwisnanto
    Xuan-Thuy Vo
    Kang-Hyun Jo
    IECON 2021 - 47TH ANNUAL CONFERENCE OF THE IEEE INDUSTRIAL ELECTRONICS SOCIETY, 2021,
  • [10] MUNet: Macro Unit-based Convolutional Neural network for Mobile Devices
    Kim, Dae Ha
    Lee, Seung Hyun
    Song, Byung Cheol
    PROCEEDINGS 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW), 2018, : 1749 - 1757
12345