Kernel Mean Matching for Content Addressability of GANs

2019/05/14 by Wittawat Jitkrittum, Patsorn Sangkloy, Jitkrittum, Wittawat +9 · 1 citation
Computer Science · Mathematics · #Advanced Image and Video Retrieval Techniques #Artificial intelligence #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Content (measure theory) #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Generative grammar #Generative model #Image (mathematics) #Kernel (algebra) #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine learning #Matching (statistics) #Mathematics #Multimodal Machine Learning Applications #Pattern recognition (psychology) #Process (computing) #Set (abstract data type) #cs.CV #cs.LG #stat.ML

paper · pdf · doi:10.48550/arxiv.1905.05882

published in arXiv (Cornell University), 3140-3151 (Cornell University) · Wittawat Jitkrittum and Patsorn Sangkloy contributed equally to this work

arxiv created 2019/05/14 · openalex publication_date 2019/05/14 · arxiv updated 2019/05/16 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05

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.

Citations

• LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
• Generative Moment Matching Networks
• Auto-Encoding Variational Bayes
• Conditional Generative Adversarial Nets
• Neural Photo Editing with Introspective Adversarial Networks
• Learning in Implicit Generative Models
• Generative Models and Model Criticism via Optimized Maximum Mean Discrepancy
• Globally and locally consistent image completion
• Multimodal Unsupervised Image-to-Image Translation
• BRUNO: A Deep Recurrent Model for Exchangeable Data
• Informative Features for Model Comparison
• Improving MMD-GAN Training with Repulsive Loss Function
• PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
• InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets

Related

• IVE-GAN: Invariant Encoding Generative Adversarial Networks
• Ways of Conditioning Generative Adversarial Networks
• Improved Techniques for Training GANs
• Generative Ratio Matching Networks
• Exploiting GAN Internal Capacity for High-Quality Reconstruction of Natural Images