Precise Recovery of Latent Vectors from Generative Adversarial Networks

Zachary C. Lipton, Subarna Tripathi

Abstract: Generative adversarial networks (GANs) transform latent vectors into visually plausible images. It is generally thought that the original GAN formulation gives no out-of-the-box method to reverse the mapping, projecting images back into latent space. We introduce a simple, gradient-based technique called stochastic clipping. In experiments, for images generated by the GAN, we exactly recover their latent vector pre-images 100% of the time. Additional experiments demonstrate that this method is robust to noise. Finally, we show that even for unseen images, our method appears to recover unique encodings.

TL;DR: In practice, a simple algorithm precisely recovers the z used to generate an image G(z) 100% of the time.

Conflicts: cs.ucsd.edu

Keywords: Computer vision, Deep learning, Unsupervised Learning