%AOjha, Utkarsh%ALi, Yijun%ALu, Jingwan%AEfros, Alexei%ALee, Yong%AShechtman, Eli%AZhang, Richard%D2021%I %K %MOSTI ID: 10320562 %PMedium: X %TFew-shot Image Generation via Cross-domain Correspondence %XTraining 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. Country unknown/Code not availablehttps://doi.org/10.1109/cvpr46437.2021.01060OSTI-MSA