Interpolation in Auto Encoders with Bridge Processes

Auto encoding models have been extensively studied in recent years. They provide an efficient framework for sample generation, as well as for analysing feature learning. Furthermore, they are efficient in performing interpolations between data-points in semantically meaningful ways. In this paper, w...

Full description

Saved in:
Bibliographic Details
Published in2020 25th International Conference on Pattern Recognition (ICPR) pp. 5973 - 5980
Main Authors Ringqvist, Carl, Butepage, Judith, Kjellstrom, Hedvig, Hult, Henrik
Format Conference Proceeding
LanguageEnglish
Published IEEE 10.01.2021
Subjects
Bridges
Games
Interpolation
Legged locomotion
Measurement
Probability distribution
Stochastic processes
Online AccessGet full text

Cover

More Information
Summary:Auto encoding models have been extensively studied in recent years. They provide an efficient framework for sample generation, as well as for analysing feature learning. Furthermore, they are efficient in performing interpolations between data-points in semantically meaningful ways. In this paper, we introduce a method for generating sequence samples from auto encoders trained on flattened sequences (e.g video sample from auto encoders trained on single frames); as well as a canonical, dimension independent method for generating stochastic interpolations. The distribution of interpolation paths is represented as the distribution of a bridge process constructed from an artificial random data generating process in the latent space, having the prior distribution as its invariant distribution.
DOI:10.1109/ICPR48806.2021.9413123