Capture and control content discrepancies via normalised flow transfer

Can Zhang*, Richard Yi Da Xu*, Xu Zhang, Wanming Huang

*Corresponding author for this work

Research output: Contribution to journalJournal articlepeer-review

Abstract

Unsupervised Style Transfer (UST) has recently been a hot topic in Computer Vision, and this type of work has been exemplified by CycleGAN. Although the existing UST methods have proven to be useful, in many circumstances, we want to be able to manage not just the transformation of a single piece of instance, but also the morphological features of the two data sets’ underlying distributions. To this end, we propose a novel framework called Normalised Flow Transfer (NFT), where a reversible probability transform using the normalised flow method is developed to transfer the data in the first domain to the second, so as to exhibit their probabilities under both domains in the mapping process. A particularly interesting application under this framework is that when the data sets in two domains contain numerous clusters based on their finite class labels, we can control the distribution pattern across the two domains and apply any constraints on the underlying distributions of the same class. The experimental results show that not only can we devise many new complex style transfer functions, but also our framework has better image generation capabilities in terms of evaluation metrics, including mean square error, inception score and Frechet inception distance.

Original languageEnglish
Pages (from-to)161-167
Number of pages7
JournalPattern Recognition Letters
Volume165
Early online date23 Dec 2022
DOIs
Publication statusPublished - Jan 2023

Scopus Subject Areas

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

User-Defined Keywords

  • Content discrepancies
  • Generative adversarial network
  • Normalised flow model
  • Unsupervised style transfer

Fingerprint

Dive into the research topics of 'Capture and control content discrepancies via normalised flow transfer'. Together they form a unique fingerprint.

Cite this