Attribute decomposition for flow-based domain mapping

Sheng Jhe Huang, Jen Tzung Chien

研究成果: Conference article同行評審

6 引文 斯高帕斯(Scopus)


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.

頁(從 - 到)1710-1714
期刊ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
出版狀態Published - 6月 2021
事件2021 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2021 - Virtual, Toronto, Canada
持續時間: 6 6月 202111 6月 2021


深入研究「Attribute decomposition for flow-based domain mapping」主題。共同形成了獨特的指紋。