Optics and Precision Engineering, Volume. 31, Issue 15, 2287(2023)

Simulating primary visual cortex to improve robustness of CNN neural network structures

Lijuan ZHANG1,2, Mengda HU2, Ziwei ZHANG2, Yutong JIANG3, and Dongming LI1、*
Author Affiliations
  • 1School of Internet of Things Engineering, Wuxi University, Wuxi2405, China
  • 2Collegel of Computer Science and Technology, Changchun University of Technology, Changchun13001, China
  • 3China North Vehicle Research Institute, Beijing100072, China
  • show less
    Figures & Tables(6)
    Schematic diagram of VVBLock
    Example images of CIFAR-10 dataset
    Images with artificial insertion of noise
    Accuracy comparison of original network and reconstructed network of VVNet on dataset Cifar10 for three common networks
    Comparison of image classification accuracy for four types of noise images using VVNet network, VOneNet network, and original network model
    • Table 1. Accuracy for three network in different architectures on dataset Cifar10

      View table
      View in Article

      Table 1. Accuracy for three network in different architectures on dataset Cifar10

      NetworkVVNetVOneNetNoneEpoch
      AlexNet0.6230.5740.61750
      DenseNet0.7870.6740.765
      VGG0.7730.6870.772
    Tools

    Get Citation

    Copy Citation Text

    Lijuan ZHANG, Mengda HU, Ziwei ZHANG, Yutong JIANG, Dongming LI. Simulating primary visual cortex to improve robustness of CNN neural network structures[J]. Optics and Precision Engineering, 2023, 31(15): 2287

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Category: Information Sciences

    Received: Feb. 14, 2023

    Accepted: --

    Published Online: Sep. 5, 2023

    The Author Email: LI Dongming (LDM0214@163.com)

    DOI:10.37188/OPE.20233115.2287

    Topics