Conditional Convolution Projecting Latent Vectors on Condition-Specific Space

Min Cheol Sagong, Yoon Jae Yeo, Yong Goo Shin, Sung Jea Ko

Research output: Contribution to journalArticlepeer-review

2 Citations (Scopus)

Abstract

Despite rapid advancements over the past several years, the conditional generative adversarial networks (cGANs) are still far from being perfect. Although one of the major concerns of the cGANs is how to provide the conditional information to the generator, there are not only no ways considered as the optimal solution but also a lack of related research. This brief presents a novel convolution layer, called the conditional convolution (cConv) layer, which incorporates the conditional information into the generator of the generative adversarial networks (GANs). Unlike the most general framework of the cGANs using the conditional batch normalization (cBN) that transforms the normalized feature maps after convolution, the proposed method directly produces conditional features by adjusting the convolutional kernels depending on the conditions. More specifically, in each cConv layer, the weights are conditioned in a simple but effective way through filter-wise scaling and channel-wise shifting operations. In contrast to the conventional methods, the proposed method with a single generator can effectively handle condition-specific characteristics. The experimental results on CIFAR, LSUN, and ImageNet datasets show that the generator with the proposed cConv layer achieves a higher quality of conditional image generation than that with the standard convolution layer.

Original languageEnglish
Pages (from-to)1-8
Number of pages8
JournalIEEE Transactions on Neural Networks and Learning Systems
DOIs
Publication statusAccepted/In press - 2022

Bibliographical note

Publisher Copyright:
IEEE

Keywords

  • Conditional image generation
  • Convolution
  • Generative adversarial networks
  • Generators
  • Image synthesis
  • Learning systems
  • Standards
  • Visualization
  • deep learning
  • generative adversarial networks (GANs).

ASJC Scopus subject areas

  • Software
  • Computer Science Applications
  • Computer Networks and Communications
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Conditional Convolution Projecting Latent Vectors on Condition-Specific Space'. Together they form a unique fingerprint.

Cite this