• English
  • Deutsch
  • Log In
    Password Login
    Research Outputs
    Fundings & Projects
    Researchers
    Institutes
    Statistics
Repository logo
Fraunhofer-Gesellschaft
  1. Home
  2. Fraunhofer-Gesellschaft
  3. Anderes
  4. Combining Transformer Generators with Convolutional Discriminators
 
  • Details
  • Full
Options
2021
Paper (Preprint, Research Paper, Review Paper, White Paper, etc.)
Title

Combining Transformer Generators with Convolutional Discriminators

Title Supplement
Published on arXiv
Abstract
Transformer models have recently attracted much interest from computer vision researchers and have since been successfully employed for several problems traditionally addressed with convolutional neural networks. At the same time, image synthesis using generative adversarial networks (GANs) has drastically improved over the last few years. The recently proposed TransGAN is the first GAN using only transformer-based architectures and achieves competitive results when compared to convolutional GANs. However, since transformers are data-hungry architectures, TransGAN requires data augmentation, an auxiliary super-resolution task during training, and a masking prior to guide the self-attention mechanism. In this paper, we study the combination of a transformer-based generator and convolutional discriminator and successfully remove the need of the aforementioned required design choices. We evaluate our approach by conducting a benchmark of well-known CNN discriminators, ablate the size of the transformer-based generator, and show that combining both architectural elements into a hybrid model leads to better results. Furthermore, we investigate the frequency spectrum properties of generated images and observe that our model retains the benefits of an attention based generator.
Author(s)
Durall, Ricard
Fraunhofer-Institut für Techno- und Wirtschaftsmathematik ITWM  
Frolov, Stanislav
Technical University of Kaiserslautern; German Research Center for Artificial Intelligence (DFKI)
Hees, Jörn
German Research Center for Artificial Intelligence (DFKI)
Raue, Federico
German Research Center for Artificial Intelligence (DFKI)
Pfreundt, Franz-Josef  
Fraunhofer-Institut für Techno- und Wirtschaftsmathematik ITWM  
Dengel, Andreas
Technical University of Kaiserslautern; German Research Center for Artificial Intelligence (DFKI)
Keuper, Janis  
Fraunhofer-Institut für Techno- und Wirtschaftsmathematik ITWM  
Link
Link
Language
English
Fraunhofer-Institut für Techno- und Wirtschaftsmathematik ITWM  
Keyword(s)
  • image synthesis

  • generative adversarial networks

  • transformers

  • hybrid models

  • Cookie settings
  • Imprint
  • Privacy policy
  • Api
  • Contact
© 2024