Keywords: disentangled representations, generative adversarial networks, generative modeling, image synthesis
TL;DR: SD-GANs disentangle latent codes according to known commonalities in a dataset (e.g. photographs depicting the same person).
Abstract: We propose a new algorithm for training generative adversarial networks to jointly learn latent codes for both identities (e.g. individual humans) and observations (e.g. specific photographs). In practice, this means that by fixing the identity portion of latent codes, we can generate diverse images of the same subject, and by fixing the observation portion we can traverse the manifold of subjects while maintaining contingent aspects such as lighting and pose. Our algorithm features a pairwise training scheme in which each sample from the generator consists of two images with a common identity code. Corresponding samples from the real dataset consist of two distinct photographs of the same subject. In order to fool the discriminator, the generator must produce images that are both photorealistic, distinct, and appear to depict the same person. We augment both the DCGAN and BEGAN approaches with Siamese discriminators to accommodate pairwise training. Experiments with human judges and an off-the-shelf face verification system demonstrate our algorithm’s ability to generate convincing, identity-matched photographs.
Code: [![github](/images/github_icon.svg) chrisdonahue/sdgan](https://github.com/chrisdonahue/sdgan)