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 similarity-based structure loss in few-shot GDA, both quantitatively and qualitatively. The code will be available at https://github.com/wuyi2020/DoRM.

翻译：本研究探究了小样本生成域迁移（GDA）任务，该任务旨在仅利用少量参考图像，将预训练生成器从一个域迁移至新域。受人类大脑在新域中获取知识方式的启发，我们提出了一种名为域重调制（DoRM）的创新生成器结构。DoRM不仅满足先前GDA研究在高质量、大合成多样性及跨域一致性方面的要求，还借鉴人类大脑运作机制，融入了记忆与域关联能力。具体而言，DoRM冻结源生成器，并引入新的映射与仿射模块（M&A模块），在GDA过程中捕获目标域的属性。该过程类似于人类大脑新突触的形成，并使得风格空间中产生线性可组合的域漂移。通过集成多个新的M&A模块，生成器可获得执行高保真多域及混合域生成的能力。此外，为更有效地保持跨域一致性，我们引入一种基于相似性的结构损失。该损失在训练过程中将目标图像的互相关图与其对应的源图像互相关图进行对齐。通过大量实验，我们从定量与定性两个角度证明了DoRM及基于相似性的结构损失在小样本GDA中的优异性能。代码将于https://github.com/wuyi2020/DoRM 公开。