Kernel Mean Matching for Content Addressability of GANs

Abstract

We propose a novel procedure which adds "content-addressability" to any given unconditional implicit model e.g., a generative adversarial network (GAN). The procedure allows users to control the generative process by specifying a set (arbitrary size) of desired examples based on which similar samples are generated from the model. The proposed approach, based on kernel mean matching, is applicable to any generative models which transform latent vectors to samples, and does not require retraining of the model. Experiments on various high-dimensional image generation problems (CelebA-HQ, LSUN bedroom, bridge, tower) show that our approach is able to generate images which are consistent with the input set, while retaining the image quality of the original model. To our knowledge, this is the first work that attempts to construct, at test time, a content-addressable generative model from a trained marginal model.

Wittawat Jitkrittum and Patsorn Sangkloy contributed equally to this work

References in corpus (15)

• Auto-Encoding Variational Bayes
• Conditional Generative Adversarial Nets
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
• Which Training Methods for GANs do actually Converge?
• Generative Moment Matching Networks
• Multimodal Unsupervised Image-to-Image Translation
• Neural Photo Editing with Introspective Adversarial Networks
• Learning in Implicit Generative Models
• Generative Models and Model Criticism via Optimized Maximum Mean Discrepancy
• Improving MMD-GAN Training with Repulsive Loss Function
• BRUNO: A Deep Recurrent Model for Exchangeable Data
• Informative Features for Model Comparison
• Learning deep kernels for exponential family densities