Emerging Disentanglement in Auto-Encoder Based Unsupervised Image Content Transfer
This addresses the problem of unsupervised domain mapping for computer vision researchers, offering a simpler alternative to existing methods, though it appears incremental in scope.
The paper tackles unsupervised image content transfer between domains by learning to map samples from domain A to domain B while replicating missing information from a reference, such as adding glasses to faces. It shows that a simple auto-encoder architecture with minimal losses ensures disentanglement between domains, with convincing results in visual tasks like adding glasses or facial hair.
We study the problem of learning to map, in an unsupervised way, between domains A and B, such that the samples b in B contain all the information that exists in samples a in A and some additional information. For example, ignoring occlusions, B can be people with glasses, A people without, and the glasses, would be the added information. When mapping a sample a from the first domain to the other domain, the missing information is replicated from an independent reference sample b in B. Thus, in the above example, we can create, for every person without glasses a version with the glasses observed in any face image. Our solution employs a single two-pathway encoder and a single decoder for both domains. The common part of the two domains and the separate part are encoded as two vectors, and the separate part is fixed at zero for domain A. The loss terms are minimal and involve reconstruction losses for the two domains and a domain confusion term. Our analysis shows that under mild assumptions, this architecture, which is much simpler than the literature guided-translation methods, is enough to ensure disentanglement between the two domains. We present convincing results in a few visual domains, such as no-glasses to glasses, adding facial hair based on a reference image, etc.