11
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Theoretical Insights into the Use of Structural Similarity Index In Generative Models and Inferential Autoencoders

      Preprint
      , ,

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          Generative models and inferential autoencoders mostly make use of \(\ell_2\) norm in their optimization objectives. In order to generate perceptually better images, this short paper theoretically discusses how to use Structural Similarity Index (SSIM) in generative models and inferential autoencoders. We first review SSIM, SSIM distance metrics, and SSIM kernel. We show that the SSIM kernel is a universal kernel and thus can be used in unconditional and conditional generated moment matching networks. Then, we explain how to use SSIM distance in variational and adversarial autoencoders and unconditional and conditional Generative Adversarial Networks (GANs). Finally, we propose to use SSIM distance rather than \(\ell_2\) norm in least squares GAN.

          Related collections

          Author and article information

          Journal
          04 April 2020
          Article
          2004.01864
          a44e6420-1363-4b74-b4e1-56a194654f03

          http://arxiv.org/licenses/nonexclusive-distrib/1.0/

          History
          Custom metadata
          Accepted (to appear) in International Conference on Image Analysis and Recognition (ICIAR) 2020, Springer
          cs.LG cs.CV eess.IV stat.ML

          Computer vision & Pattern recognition,Machine learning,Artificial intelligence,Electrical engineering

          Comments

          Comment on this article