Disentangling Factors of Variation by Mixing Them

Understand

We propose an approach to learn image representations that consist of disentangled factors of variation without exploiting any manual labeling or data domain knowledge.

• A factor of variation corresponds to an image attribute that can be discerned consistently across a set of images, such as the pose or color of objects.
• Our disentangled representation consists of a concatenation of feature chunks, each chunk representing a factor of variation.
• It supports applications such as transferring attributes from one image to another, by simply mixing and unmixing feature chunks, and classification or retrieval based on one or several attributes, by considering a user-specified subset of feature chunks.