Journals Articles Conferences News About CLP
Submit a paper Email Alert
Search
Search
Articles
Journals
News
Advanced Search
Top Searches
2D MaterialsTransformation opticsQuantum PhotonicsSmall lasersSemiconductor UV PhotonicsSupersymmetric microring laser arrays

Laser & Optoelectronics Progress, Volume. 57, Issue 18, 181504(2020)

Image Generation Method for Adversarial Network Based on Residual Structure

Bei Yan1,2、*, Li Zhang1,2, Jianlin Zhang1,2, and Zhiyong Xu1,2
Author Affiliations
  • 1Institute of Optics and Electronics, Chinese Academy of Sciences, Chengdu, Sichuan 610209, China
  • 2University of Chinese Academy of Sciences, Beijing 100049, China
    • show less
    AbstractGet PDF(in Chinese)
    Figures&Tables (14)
    Equations (0)
    References (21)
    Cited By (1)
    Tools
    Paper Information
    Topics
    Figures & Tables(14)
    Flow chart of GAN

    Fig. 1. Flow chart of GAN

    Download full size
    Structure of RBU

    Fig. 2. Structure of RBU

    Download full size
    RBU of generator

    Fig. 3. RBU of generator

    Download full size
    Generator model

    Fig. 4. Generator model

    Download full size
    RBU of discriminator

    Fig. 5. RBU of discriminator

    Download full size
    Discriminator model

    Fig. 6. Discriminator model

    Download full size
    Generated images of SVHN dataset under different epochs

    Fig. 7. Generated images of SVHN dataset under different epochs

    Download full size
    Generated images of Cifar-10 dataset under different epochs

    Fig. 8. Generated images of Cifar-10 dataset under different epochs

    Download full size
    Generated images of CelebA dataset under different epochs

    Fig. 9. Generated images of CelebA dataset under different epochs

    Download full size
    Generated images of each dataset after 200 epochs

    Fig. 10. Generated images of each dataset after 200 epochs

    Download full size
    IS change on SVHN dataset

    Fig. 11. IS change on SVHN dataset

    Download full size
    IS change on Cifar-10 dataset

    Fig. 12. IS change on Cifar-10 dataset

    Download full size
    IS change on CelebA dataset

    Fig. 13. IS change on CelebA dataset

    Download full size

    • Table 1. IS of different datasets

      View table

      Table 1. IS of different datasets

      DatasetMethod100 epochs200 epochs500 epochs800 epochs1000 epochs
      SVHNDCGAN2.78±0.072.74±0.052.70±0.062.42±0.042.41±0.06
      Proposed method3.57±0.163.94±0.183.92±0.183.95±0.233.90±0.22
      Cifar-10DCGAN4.90±0.214.85±0.194.26±0.194.24±0.194.55±0.66
      Proposed method5.88±0.206.09±0.246.15±0.256.10±0.186.18±0.30
      CelebADCGAN2.61±0.072.52±0.022.48±0.062.76±0.062.16±0.05
      Proposed method3.32±0.043.12±0.093.24±0.073.27±0.123.23±0.08
    Tools

    Get Citation

    Copy Citation Text

    Bei Yan, Li Zhang, Jianlin Zhang, Zhiyong Xu. Image Generation Method for Adversarial Network Based on Residual Structure[J]. Laser & Optoelectronics Progress, 2020, 57(18): 181504

    Download Citation

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

    Category: Machine Vision

    Received: Jan. 2, 2020

    Accepted: Feb. 10, 2020

    Published Online: Sep. 2, 2020

    The Author Email: Yan Bei (yanbei6412@163.com)

    DOI:10.3788/LOP57.181504

    Topics

    laser devices and laser physics
    Lasers and Laser Optics
    Laser physics
    laser manufacturing
    Instrumentation, Measurement and Metrology