SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2209.03665 · NeurIPS · 2022

Generalized One-shot Domain Adaptation of Generative Adversarial Networks

Ting Yao, Tao Mei, Zicheng Zhang, Yinglu Liu, Congying Han, Tiande Guo

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

Figure 1: Illustrations of the generalized one-shot GAN adaptation task. Target images with the corresponding binary entity masks are provided to adapt the pre-trained GAN to the domain of similar style and entity as target images. The first three masks are all zeros and the others have value 1 in the areas bounded by green lines. Our adapted model is of strong cross-domain correspondence to realize both style and entity transfer.

For agents

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

get_harvested_code_for_paper("2209.03665")
get_code_for_paper("2209.03665")
have("2209.03665")

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

curl https://syntology.ai/api/ran/2209.03665.json

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

[![Syntology run record](https://syntology.ai/api/ran/2209.03665.svg)](https://syntology.ai/paper/2209.03665)

Connect an agent — have() is free.