SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2302.02550 · NeurIPS · 2023

Domain Re-Modulation for Few-Shot Generative Domain Adaptation

Dacheng Tao, Bin Li, Yi Wu, Chaoyue Wang, Heliang Zheng, Ziqiang Li, Shanshan Zhao

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

In this study, we delve into the task of few-shot Generative Domain Adaptation (GDA), which involves transferring a pre-trained generator from one domain to a new domain using only a few reference images. Inspired by the way human brains acquire knowledge in new domains, we present an innovative generator structure called Domain Re-Modulation (DoRM). DoRM not only meets the criteria of high quality, large synthesis diversity, and cross-domain consistency, which were achieved by previous research in GDA, but also incorporates memory and domain association, akin to how human brains operate. Specifically, DoRM freezes the source generator and introduces new mapping and affine modules (M&A modules) to capture the attributes of the target domain during GDA. This process resembles the formation of new synapses in human brains. Consequently, a linearly combinable domain shift occurs in the style space. By incorporating multiple new M&A modules, the generator gains the capability to perform high-fidelity multi-domain and hybrid-domain generation. Moreover, to maintain cross-domain consistency more effectively, we introduce a similarity-based structure loss. This loss aligns the auto-correlation map of the target image with its corresponding auto-correlation map of the source image during training. Through extensive experiments, we demonstrate the superior performance of our DoRM and similaritybased structure loss in few-shot GDA, both quantitatively and qualitatively. Code will be available at https://github.com/wuyi2020/DoRM.

For agents

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

get_harvested_code_for_paper("2302.02550")
get_code_for_paper("2302.02550")
have("2302.02550")

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

curl https://syntology.ai/api/ran/2302.02550.json

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

[![Syntology run record](https://syntology.ai/api/ran/2302.02550.svg)](https://syntology.ai/paper/2302.02550)

Connect an agent — have() is free.