Skip to yearly menu bar Skip to main content

Workshop: Symmetry and Geometry in Neural Representations

Self-Supervised Latent Symmetry Discovery via Class-Pose Decomposition

Gustaf Tegnér · Hedvig Kjellstrom


In this paper, we explore the discovery of latent symmetries of data in a self-supervised manner. By considering sequences of observations undergoing uniform motion, we can extract a shared group transformation from the latent observations. In contrast to previous work, we utilize a latent space in which the group and orbit component are decomposed. We show that this construction facilitates more accurate identification of the properties of the underlying group, which consequently results in an improved performance on a set of sequential prediction tasks.

Chat is not available.