Cross-modal Variational Auto-encoder with Distributed Latent Spaces and Associators

Jo, Dae Ung, Lee, ByeongJu, Choi, Jongwon, Yoo, Haanju, Choi, Jin Young

arXiv.org Machine Learning 

In this paper, we propose a novel structure for a cross-modal data association, which is inspired by the recent research on the associative learning structure of the brain. We formulate the cross-modal association in Bayesian inference framework realized by a deep neural network with multiple variational auto-encoders and variational associators. The variational associators transfer the latent spaces between auto-encoders that represent different modalities. The proposed structure successfully associates even heterogeneous modal data and easily incorporates the additional modality to the entire network via the proposed cross-modal associator. Furthermore, the proposed structure can be trained with only a small amount of paired data since auto-encoders can be trained by unsupervised manner. Through experiments, the effectiveness of the proposed structure is validated on various datasets including visual and auditory data.

Duplicate Docs Excel Report

Title
None found

Similar Docs  Excel Report  more

TitleSimilaritySource
None found