The Hessian Penalty: A Weak Prior for Unsupervised Disentanglement

Understand

Existing disentanglement methods for deep generative models rely on hand-picked priors and complex encoder-based architectures.

• In this paper, we propose the Hessian Penalty, a simple regularization term that encourages the Hessian of a generative model with respect to its input to be diagonal.
• We introduce a model-agnostic, unbiased stochastic approximation of this term based on Hutchinson's estimator to compute it efficiently during training.
• Our method can be applied to a wide range of deep generators with just a few lines of code.