Attribute decomposition for flow-based domain mapping

Sheng Jhe Huang, Jen Tzung Chien

Research output: Contribution to journalConference articlepeer-review

4 Scopus citations


Domain mapping aims to estimate a sophisticated mapping between source and target domains. Finding the specialized attribute in latent representation plays a key role to attain a desirable performance. However, the entangled features usually contain the mixed attribute which can not be easily decomposed in an unsupervised manner. To handle the mixed features for better generation, this paper presents an attribute decomposition based on the sequence data and carries out the flow-based image domain mapping. The latent variables, characterized by flow model, are decomposed into the attribute-relevant and attribute-irrelevant components. The decomposition is guided by multiple objectives including structural-perceptual loss, cycle consistency loss, sequential random-pair reconstruction loss and sequential classification loss where the paired training data for domain mapping are not required. Importantly, the sequential random-pair reconstruction loss is formulated by means of exchanging the attribute-relevant components within a sequence of images. As a result, the source images with the attributes of reference images can be smoothly transferred to the corresponding target images. Experiments on talking face synthesis show the merit of attribute decomposition in domain mapping.

Original languageEnglish
Pages (from-to)1710-1714
Number of pages5
JournalICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
StatePublished - Jun 2021
Event2021 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2021 - Virtual, Toronto, Canada
Duration: 6 Jun 202111 Jun 2021


  • Domain mapping
  • Flow-based model
  • Generative model
  • Image synthesis
  • Talking face generation


Dive into the research topics of 'Attribute decomposition for flow-based domain mapping'. Together they form a unique fingerprint.

Cite this