SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2012.02780 · NeurIPS · 2020

Few-shot Image Generation with Elastic Weight Consolidation

Richard Zhang, Jingwan Lu, Eli Shechtman, Yijun Li

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. We have no repository linked to it either. That is a statement about our graph, not about the paper.

Abstract

Few-shot image generation seeks to generate more data of a given domain, with only few available training examples. As it is unreasonable to expect to fully infer the distribution from just a few observations (e.g., emojis), we seek to leverage a large, related source domain as pretraining (e.g., human faces). Thus, we wish to preserve the diversity of the source domain, while adapting to the appearance of the target. We adapt a pretrained model, without introducing any additional parameters, to the few examples of the target domain. Crucially, we regularize the changes of the weights during this adaptation, in order to best preserve the "information" of the source dataset, while fitting the target. We demonstrate the effectiveness of our algorithm by generating high-quality results of different target domains, including those with extremely few examples (e.g., ≤10). We also analyze the performance of our method with respect to some important factors, such as the number of examples and the dissimilarity between the source and target domain.

For agents

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

get_harvested_code_for_paper("2012.02780")
get_code_for_paper("2012.02780")
have("2012.02780")

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

curl https://syntology.ai/api/ran/2012.02780.json

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

[![Syntology run record](https://syntology.ai/api/ran/2012.02780.svg)](https://syntology.ai/paper/2012.02780)

Connect an agent — have() is free.