SUGAN: A Stable U-Net Based Generative Adversarial Network

Shijie Cheng, Lingfeng Wang, Min Zhang, Cheng Zeng, Yan Meng

Research output: Journal article publicationJournal articleAcademic researchpeer-review

2 Citations (Scopus)

Abstract

As one of the representative models in the field of image generation, generative adversarial networks (GANs) face a significant challenge: how to make the best trade-off between the quality of generated images and training stability. The U-Net based GAN (U-Net GAN), a recently developed approach, can generate high-quality synthetic images by using a U-Net architecture for the discriminator. However, this model may suffer from severe mode collapse. In this study, a stable U-Net GAN (SUGAN) is proposed to mainly solve this problem. First, a gradient normalization module is introduced to the discriminator of U-Net GAN. This module effectively reduces gradient magnitudes, thereby greatly alleviating the problems of gradient instability and overfitting. As a result, the training stability of the GAN model is improved. Additionally, in order to solve the problem of blurred edges of the generated images, a modified residual network is used in the generator. This modification enhances its ability to capture image details, leading to higher-definition generated images. Extensive experiments conducted on several datasets show that the proposed SUGAN significantly improves over the Inception Score (IS) and Fréchet Inception Distance (FID) metrics compared with several state-of-the-art and classic GANs. The training process of our SUGAN is stable, and the quality and diversity of the generated samples are higher. This clearly demonstrates the effectiveness of our approach for image generation tasks. The source code and trained model of our SUGAN have been publicly released.

Original languageEnglish
Article number7338
JournalSensors
Volume23
Issue number17
DOIs
Publication statusPublished - Sept 2023

Keywords

  • generative adversarial network
  • gradient normalization
  • image generation
  • mode collapse
  • training stability

ASJC Scopus subject areas

  • Analytical Chemistry
  • Information Systems
  • Atomic and Molecular Physics, and Optics
  • Biochemistry
  • Instrumentation
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'SUGAN: A Stable U-Net Based Generative Adversarial Network'. Together they form a unique fingerprint.

Cite this