D3T-GAN: Data-Dependent Domain Transfer GANs for Few-shot Image Generation
This addresses the problem of generating realistic images with limited data for AI and computer vision applications, representing an incremental advance in transfer learning for GANs.
The paper tackles few-shot image generation by proposing D3T-GAN, a self-supervised transfer scheme that improves image quality and achieves state-of-the-art FID scores on common datasets.
As an important and challenging problem, few-shot image generation aims at generating realistic images through training a GAN model given few samples. A typical solution for few-shot generation is to transfer a well-trained GAN model from a data-rich source domain to the data-deficient target domain. In this paper, we propose a novel self-supervised transfer scheme termed D3T-GAN, addressing the cross-domain GANs transfer in few-shot image generation. Specifically, we design two individual strategies to transfer knowledge between generators and discriminators, respectively. To transfer knowledge between generators, we conduct a data-dependent transformation, which projects and reconstructs the target samples into the source generator space. Then, we perform knowledge transfer from transformed samples to generated samples. To transfer knowledge between discriminators, we design a multi-level discriminant knowledge distillation from the source discriminator to the target discriminator on both the real and fake samples. Extensive experiments show that our method improve the quality of generated images and achieves the state-of-the-art FID scores on commonly used datasets.