# Kernel Mean Matching for Content Addressability of GANs

arXiv: https://arxiv.org/abs/1905.05882 · HTML: https://mlsanity.com/paper/1905.05882/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 May 2019.

## Built on by (most cited first, 5 of 5)

- [Reverse Engineering of Generative Models: Inferring Model Hyperparameters from Generated Images](https://mlsanity.com/paper/2106.07873/) (2021)
- [Reproducing kernel Hilbert C*-module and kernel mean embeddings](https://mlsanity.com/paper/2101.11410/) (2021)
- [Submodular Framework for Structured-Sparse Optimal Transport](https://mlsanity.com/paper/2406.04914/) (2024)
- [MineGAN++: Mining Generative Models for Efficient Knowledge Transfer to Limited Data Domains](https://mlsanity.com/paper/2104.13742/) (2021)
- [Domain Adaptation for Inertial Measurement Unit-based Human Activity Recognition: A Survey](https://mlsanity.com/paper/2304.06489/) (2023)

## Abstract (arXiv)

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.