Adversarial Information Factorization

TL;DR

This paper introduces a new generative model architecture that learns to separate object identity from specific attributes in images, enabling attribute manipulation and achieving state-of-the-art classification results.

Contribution

The paper presents a novel model that factorizes image representations into identity and attribute components, facilitating attribute editing without altering object identity.

Findings

Successful attribute manipulation in images

State-of-the-art facial attribute classification scores

Effective disentanglement of identity and attributes

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.