Generative Adversarial Network with Multi-Branch Discriminator for Cross-Species Image-to-Image Translation

2019/01/24 by Ziqiang Zheng, Zhibin Yu, Zheng, Ziqiang +9 · 4 citations
Computer Science · #Advanced Image Processing Techniques #Adversarial system #Artificial intelligence #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Computer vision #Digital Media Forensic Detection #Discriminator #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Generative adversarial network #Generative grammar #Image (mathematics) #Image translation #Machine Learning (cs.LG) #Pattern recognition (psychology) #Telecommunications #Translation (biology) #cs.CV #cs.LG

paper · pdf · doi:10.48550/arxiv.1901.10895

published in arXiv (Cornell University) (Cornell University) · 10 pages, 16 figures

arxiv created 2019/01/24 · openalex publication_date 2019/01/24 · arxiv updated 2019/01/31 · openalex created_date 2019/03/11 · openalex updated_date 2026/07/28

Abstract

Current approaches have made great progress on image-to-image translation tasks benefiting from the success of image synthesis methods especially generative adversarial networks (GANs). However, existing methods are limited to handling translation tasks between two species while keeping the content matching on the semantic level. A more challenging task would be the translation among more than two species. To explore this new area, we propose a simple yet effective structure of a multi-branch discriminator for enhancing an arbitrary generative adversarial architecture (GAN), named GAN-MBD. It takes advantage of the boosting strategy to break a common discriminator into several smaller ones with fewer parameters, which can enhance the generation and synthesis abilities of GANs efficiently and effectively. Comprehensive experiments show that the proposed multi-branch discriminator can dramatically improve the performance of popular GANs on cross-species image-to-image translation tasks while reducing the number of parameters for computation. The code and some datasets are attached as supplementary materials for reference.

Citations

• Auto-Encoding Variational Bayes
• Generative Adversarial Text to Image Synthesis
• Unsupervised Cross-Domain Image Generation
• Generative Multi-Adversarial Networks
• Learning to Discover Cross-Domain Relations with Generative Adversarial Networks
• Face Super-Resolution Through Wasserstein GANs
• An Introduction to Image Synthesis with Generative Adversarial Nets
• Cross Domain Image Generation through Latent Space Exploration with Adversarial Loss
• Twin-GAN -- Unpaired Cross-Domain Image Translation with Weight-Sharing GANs
• Improved Techniques for GAN based Facial Inpainting
• MD-GAN: Multi-Discriminator Generative Adversarial Networks for Distributed Datasets

Related

• Mechanisms of Generative Image-to-Image Translation Networks
• Crossing-Domain Generative Adversarial Networks for Unsupervised Multi-Domain Image-to-Image Translation
• SingleGAN: Image-to-Image Translation by a Single-Generator Network using Multiple Generative Adversarial Learning
• Comparison and Analysis of Image-to-Image Generative Adversarial Networks: A Survey
• Discriminative Region Proposal Adversarial Networks for High-Quality Image-to-Image Translation