Training generative models, such as GANs, on a target domain containing limited examples (e.g., 10) can easily result in overfitting. In this work, we seek to utilize a large source domain for pretraining and transfer the diversity information from source to target. We propose to preserve the relative similarities and differences between instances in the source via a novel cross-domain distance consistency loss. To further reduce overfitting, we present an anchor-based strategy to encourage different levels of realism over different regions in the latent space. With extensive results in both photorealistic and non-photorealistic domains, we demonstrate qualitatively and quantitatively that our few-shot model automatically discovers correspondences between source and target domains and generates more diverse and realistic images than previous methods.

中文翻译：

---

通过跨域对应生成少量镜头图像

在包含有限示例（例如10个）的目标域上训练生成模型，例如GAN，很容易导致过度拟合。在这项工作中，我们试图利用大型源域进行预训练，并将多样性信息从源传递到目标。我们建议通过新颖的跨域距离一致性损失来保留源中实例之间的相对相似性和差异。为了进一步减少过度拟合，我们提出了一种基于锚点的策略，以鼓励在潜在空间中不同区域的不同级别的真实感。在真实感和非真实感领域都获得了广泛的成果，