Variation Network: Learning High-level Attributes for Controlled Input Manipulation

Gaëtan Hadjeres

Abstract: 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 be easily combined which makes VarNet applicable for a wide variety of tasks. Further, VarNet has a sound probabilistic interpretation which grants us with a novel way to navigate in the latent spaces as well as means to control how the attributes are learned. We demonstrate experimentally that this model is capable of performing interesting input manipulation and that the learned attributes are relevant and interpretable.

Keywords: Generative models, Input manipulation, Unsupervised feature learning, Variations

TL;DR: The Variation Network is a generative model able to learn high-level attributes without supervision that can then be used for controlled input manipulation.

Code: [ Ghadjeres/VarNet](https://github.com/Ghadjeres/VarNet)

Data: [CelebA](https://paperswithcode.com/dataset/celeba), [Fashion-MNIST](https://paperswithcode.com/dataset/fashion-mnist), [dSprites](https://paperswithcode.com/dataset/dsprites)

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/variation-network-learning-high-level/code)