Adversarial Information Factorization

Abstract

We propose a novel generative model architecture designed to learn representations for images that factor out a single attribute from the rest of the representation. A single object may have many attributes which when altered do not change the identity of the object itself. Consider the human face; the identity of a particular person is independent of whether or not they happen to be wearing glasses. The attribute of wearing glasses can be changed without changing the identity of the person. However, the ability to manipulate and alter image attributes without altering the object identity is not a trivial task. Here, we are interested in learning a representation of the image that separates the identity of an object (such as a human face) from an attribute (such as 'wearing glasses'). We demonstrate the success of our factorization approach by using the learned representation to synthesize the same face with and without a chosen attribute. We refer to this specific synthesis process as image attribute manipulation. We further demonstrate that our model achieves competitive scores, with state of the art, on a facial attribute classification task.

References in corpus (3)

• Conditional Image Synthesis With Auxiliary Classifier GANs
• Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
• Multi-label Learning Based Deep Transfer Neural Network for Facial Attribute Classification

Cited by in corpus (7)

• Lifelong Teacher-Student Network Learning
• 3DMolNet: A Generative Network for Molecular Structures
• Disentanglement Learning for Variational Autoencoders Applied to Audio-Visual Speech Enhancement
• MMP++: Motion Manifold Primitives with Parametric Curve Models
• Learning Conditional Invariance through Cycle Consistency
• Inverse Learning of Symmetries
• Learning Calibratable Policies using Programmatic Style-Consistency