Multifactor Sequential Disentanglement via Structured Koopman Autoencoders

Understand

Disentangling complex data to its latent factors of variation is a fundamental task in representation learning.

• Existing work on sequential disentanglement mostly provides two factor representations, i.e., it separates the data to time-varying and time-invariant factors.
• In contrast, we consider multifactor disentanglement in which multiple (more than two) semantic disentangled components are generated.
• Key to our approach is a strong inductive bias where we assume that the underlying dynamics can be represented linearly in the latent space.