IDEAS home Printed from https://ideas.repec.org/a/plo/pone00/0271225.html
   My bibliography  Save this article

A lightweight deep neural network with higher accuracy

Author

Listed:
  • Liquan Zhao
  • Leilei Wang
  • Yanfei Jia
  • Ying Cui

Abstract

To improve accuracy of the MobileNet network, a new lightweight deep neural network is designed based on the MobileNetV2 network. Firstly, it modifies the network depth of MobileNetV2 to balance the image resolution, network width and depth to keep the gradient stable, which reduces the generation of gradient vanishing or gradient exploding. Secondly, it proposes an improved Bottleneck module by introducing channel attention mechanism. It assigns different weights for different channels according to the degree of relevance between the object features and channels. Therefore, the network can extract more effective features from a complex background. In the end, a new usage strategy of the improved Bottleneck is proposed. It uses the improved Bottleneck module in the second, fourth and fifth stages of MobileNetV2, and uses the original Bottleneck module in other states. Compared with MobileNetV2, MobileNetV3, ShuffleNetV2, GhostNet and HBONetmethods, the proposed method has the highest classification accuracy on the ImageNet-1K dataset, CIFAR-10 and CIFAR-100. Compared with YOLOV4-Lite methods based on these lightweight network networks, YOLOV4-Lite based on our proposed network also has the highest detection accuracy on the PASCAL VOC07+12 dataset.

Suggested Citation

  • Liquan Zhao & Leilei Wang & Yanfei Jia & Ying Cui, 2022. "A lightweight deep neural network with higher accuracy," PLOS ONE, Public Library of Science, vol. 17(8), pages 1-15, August.
  • Handle: RePEc:plo:pone00:0271225
    DOI: 10.1371/journal.pone.0271225
    as

    Download full text from publisher

    File URL: https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0271225
    Download Restriction: no

    File URL: https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0271225&type=printable
    Download Restriction: no

    File URL: https://libkey.io/10.1371/journal.pone.0271225?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    References listed on IDEAS

    as
    1. Hui Han & Lina Hao & Dequan Cheng & He Xu, 2020. "GAN-SAE based fault diagnosis method for electrically driven feed pumps," PLOS ONE, Public Library of Science, vol. 15(10), pages 1-17, October.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Rui Zhang & Jiyan Yi & Hesheng Tang & Jiawei Xiang & Yan Ren, 2022. "Fault Diagnosis Method of Waterproof Valves in Engineering Mixing Machinery Based on a New Adaptive Feature Extraction Model," Energies, MDPI, vol. 15(8), pages 1-18, April.

    More about this item

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:plo:pone00:0271225. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: plosone (email available below). General contact details of provider: https://journals.plos.org/plosone/ .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.