SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1805.01677 · 2018

Transferring GANs: generating images from limited data

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

Transferring the knowledge of pretrained networks to new domains by means of finetuning is a widely used practice for applications based on discriminative models. To the best of our knowledge this practice has not been studied within the context of generative deep networks. Therefore, we study domain adaptation applied to image generation with generative adversarial networks. We evaluate several aspects of domain adaptation, including the impact of target domain size, the relative distance between source and target domain, and the initialization of conditional GANs. Our results show that using knowledge from pretrained networks can shorten the convergence time and can significantly improve the quality of the generated images, especially when the target data is limited. We show that these conclusions can also be drawn for conditional GANs even when the pretrained model was trained without conditioning. Our results also suggest that density may be more important than diversity and a dataset with one or few densely sampled classes may be a better source model than more diverse datasets such as ImageNet or Places.

For agents

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

get_harvested_code_for_paper("1805.01677")
get_code_for_paper("1805.01677")
have("1805.01677")

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

curl https://syntology.ai/api/ran/1805.01677.json

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

[![Syntology run record](https://syntology.ai/api/ran/1805.01677.svg)](https://syntology.ai/paper/1805.01677)

Connect an agent — have() is free.