We further introduce a multi-scale diversity penalty that operates in the feature space of our discriminators.

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) .

In many unpaired image domain translation problems, e.g., style transfer or super-resolution, it is important to keep the translated image similar to its respective input image.

Achieving a balance between image quality (precision) and diversity (recall) is a significant challenge in the domain of generative models.

We further encourage the generator to adversarially learn from the self-supervised discriminator by generating augmentation-predictable real and not fake data.

Our investigation starts with the classic generative adversarial networks (GANs). Inspired by the GAN training objective, we propose a novel "distance" between the latent and data distributions, whose minimization

The evaluation of generative models has received significant attention in the machine learning community.