Variation Network: Learning High-level Attributes for Controlled Input Manipulation
This work addresses the need for flexible generative models in AI that can automatically discover and manipulate attributes, though it appears incremental as it builds on existing generative frameworks.
The paper tackles the problem of controlled input manipulation by learning high-level attributes, introducing the Variation Network (VarNet) that can handle both pre-defined and self-learned attributes, with experimental demonstration of meaningful manipulations.
This paper presents the Variation Network (VarNet), a generative model providing means to manipulate the high-level attributes of a given input. The originality of our approach is that VarNet is not only capable of handling pre-defined attributes but can also learn the relevant attributes of the dataset by itself. These two settings can also be easily considered at the same time, which makes this model applicable to a wide variety of tasks. Further, VarNet has a sound information-theoretic interpretation which grants us with interpretable means to control how these high-level attributes are learned. We demonstrate experimentally that this model is capable of performing interesting input manipulation and that the learned attributes are relevant and meaningful.