SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1811.00152 · 2018

Mixture Density Generative Adversarial Networks

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Generative Adversarial Networks have surprising ability for generating sharp and realistic images, though they are known to suffer from the so-called mode collapse problem. In this paper, we propose a new GAN variant called Mixture Density GAN that while being capable of generating high-quality images, overcomes this problem by encouraging the Discriminator to form clusters in its embedding space, which in turn leads the Generator to exploit these and discover different modes in the data. This is achieved by positioning Gaussian density functions in the corners of a simplex, using the resulting Gaussian mixture as a likelihood function over discriminator embeddings, and formulating an objective function for GAN training that is based on these likelihoods. We demonstrate empirically (1) the quality of the generated images in Mixture Density GAN and their strong similarity to real images, as measured by the Fréchet Inception Distance (FID), which compares very favourably with state-of-the-art methods, and (2) the ability to avoid mode collapse and discover all data modes.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1811.00152")
get_code_for_paper("1811.00152")
have("1811.00152")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1811.00152.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1811.00152.svg)](https://syntology.ai/paper/1811.00152)

Connect an agent — have() is free.