• myGriffith
    • Staff portal
    • Contact Us⌄
      • Future student enquiries 1800 677 728
      • Current student enquiries 1800 154 055
      • International enquiries +61 7 3735 6425
      • General enquiries 07 3735 7111
      • Online enquiries
      • Staff phonebook
    View Item 
    •   Home
    • Griffith Research Online
    • Journal articles
    • View Item
    • Home
    • Griffith Research Online
    • Journal articles
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Browse

  • All of Griffith Research Online
    • Communities & Collections
    • Authors
    • By Issue Date
    • Titles
  • This Collection
    • Authors
    • By Issue Date
    • Titles
  • Statistics

  • Most Popular Items
  • Statistics by Country
  • Most Popular Authors
  • Support

  • Contact us
  • FAQs
  • Admin login

  • Login
  • Early prediction for mode anomaly in generative adversarial network training: An empirical study

    Author(s)
    Guo, C
    Huang, D
    Zhang, J
    Xu, J
    Bai, G
    Dong, N
    Griffith University Author(s)
    Bai, Guangdong
    Year published
    2020
    Metadata
    Show full item record
    Abstract
    Mode anomaly (MA for short) significantly blocks the application of generative adversarial networks (GANs). Although diverse metrics have been proposed to measure the MA, and a lot of efforts have been made to resolve the MA, none of them gives a quantitative definition for MA detection. Moreover, very few studies concentrate on the early-stage prediction of MA. In this paper, we make the first effort to this field with a systematic empirical study. To this end, we first give a fine-grained definition where the MA is categorized into three typical sub-patterns. Afterwards, traditional MA metrics are studied with extensive ...
    View more >
    Mode anomaly (MA for short) significantly blocks the application of generative adversarial networks (GANs). Although diverse metrics have been proposed to measure the MA, and a lot of efforts have been made to resolve the MA, none of them gives a quantitative definition for MA detection. Moreover, very few studies concentrate on the early-stage prediction of MA. In this paper, we make the first effort to this field with a systematic empirical study. To this end, we first give a fine-grained definition where the MA is categorized into three typical sub-patterns. Afterwards, traditional MA metrics are studied with extensive experiments on numbers of representative combinations of subjects (including 13 GANs and 3 datasets) to explore their sensitivity for the MA across different training steps. We find that in most of cases, the MA can be reasonably predicted in very early training stage through our sensitivity studies. Under the insight, we propose a novel prediction strategy using conception of “anomaly sign”. The evaluation results on diverse experimental subjects demonstrate the feasibility and high accuracy for the early prediction of MA. We also discuss the prediction efficiency, as well as analyze the prediction effectiveness from human perception.
    View less >
    Journal Title
    Information Sciences
    Volume
    534
    DOI
    https://doi.org/10.1016/j.ins.2020.05.046
    Subject
    Mathematical sciences
    Engineering
    Publication URI
    http://hdl.handle.net/10072/400800
    Collection
    • Journal articles

    Footer

    Disclaimer

    • Privacy policy
    • Copyright matters
    • CRICOS Provider - 00233E
    • TEQSA: PRV12076

    Tagline

    • Gold Coast
    • Logan
    • Brisbane - Queensland, Australia
    First Peoples of Australia
    • Aboriginal
    • Torres Strait Islander