Performing Effective Generative Learning from a Single Image Only

Qihui Xu, Jinshu Chen, Jiacheng Tang, Qi Kang, Meng Chu Zhou

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations

Abstract

Generative adversarial networks (GANs) can be well used for image generation. Yet their training typically requires large amounts of data, which may not be available. This paper proposes a new algorithm for effective generative learning given a single image only. The proposed method involves building GAN models with a hierarchical pyramid structure and a parallel-branch design that enables independent learning of the foreground and background areas. This work conducts a set of well-designed experiments. The results well demonstrate that the proposed method produces the images of higher quality and better diversity than existing methods do. Thus, this work advances the field of generative learning for image generation.

Original languageEnglish (US)
Title of host publication32nd Wireless and Optical Communications Conference, WOCC 2023
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798350337150
DOIs
StatePublished - 2023
Event32nd Wireless and Optical Communications Conference, WOCC 2023 - Newark, United States
Duration: May 5 2023May 6 2023

Publication series

Name32nd Wireless and Optical Communications Conference, WOCC 2023

Conference

Conference32nd Wireless and Optical Communications Conference, WOCC 2023
Country/TerritoryUnited States
CityNewark
Period5/5/235/6/23

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Signal Processing
  • Control and Optimization
  • Atomic and Molecular Physics, and Optics

Keywords

  • Image generation
  • few-shot learning
  • generative adversarial networks

Fingerprint

Dive into the research topics of 'Performing Effective Generative Learning from a Single Image Only'. Together they form a unique fingerprint.

Cite this