Kernel Mean Matching for Content Addressability of GANs
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.
Code (1)
Tasks
Generative Adversarial NetworkImage GenerationSimilar Papers 제목 키워드 기반
Demystifying MMD GANs
We investigate the training and performance of generative adversarial networks using the Maximum Mean Discrepancy (MMD) as critic, termed MMD GANs. As our main theoretical contribution, we clarify the situation with bias…
Pattern Denoising in Molecular Associative Memory using Pairwise Markov Random Field Models
We propose an in silico molecular associative memory model for pattern learning, storage and denoising using Pairwise Markov Random Field (PMRF) model. Our PMRF-based molecular associative memory model extracts locally d…
DenoisingExploring Content Relationships for Distilling Efficient GANs
This paper proposes a content relationship distillation (CRD) to tackle the over-parameterized generative adversarial networks (GANs) for the serviceability in cutting-edge devices. In contrast to traditional instance-le…
TripletKernel Exponential Family Estimation via Doubly Dual Embedding
We investigate penalized maximum log-likelihood estimation for exponential family distributions whose natural parameter resides in a reproducing kernel Hilbert space. Key to our approach is a novel technique, doubly dual…
A Mean-Field Theory for Kernel Alignment with Random Features in Generative Adverserial Networks
We propose a novel supervised learning method to optimize the kernel in maximum mean discrepancy generative adversarial networks (MMD GANs). Specifically, we characterize a distributionally robust optimization problem to…