A review of disentangled representation learning for visual data processing and analysis

Abstract

： Representation learning is essential for machine learning technique nowadays. The transition of input represen⁃ tations have been developing intensively in algorithm performance benefited from the growth of hand - crafted features to the representation for multi - media data. However ， the representations of visual data are often highly entangled. The interpreta⁃ tion challenges are to be faced because all information components are encoded into the same feature space. Disentangled representation learning （ DRL ） aims to learn a low - dimensional interpretable abstract representation that can sort the mul⁃ tiple factors of variation out in high - dimensional observations. In the disentangled representation ， we can capture and manipulate the information of a single factor of variation through the corresponding latent subspace ， which makes it more