%0 Conference Proceedings
%T Distilling GANs with Style-Mixed Triplets for X2I Translation with Limited Data
%A Yaxing Wang
%A Joost Van de Weijer
%A Lu Yu
%A Shangling Jui
%B 10th International Conference on Learning Representations
%D 2022
%F Yaxing Wang2022
%O LAMP; 600.147
%O exported from refbase (http://158.109.8.37/show.php?record=3791), last updated on Mon, 30 Oct 2023 12:07:36 +0100
%X Conditional image synthesis is an integral part of many X2I translation systems, including image-to-image, text-to-image and audio-to-image translation systems. Training these large systems generally requires huge amounts of training data. Therefore, we investigate knowledge distillation to transfer knowledge from a high-quality unconditioned generative model (e.g., StyleGAN) to a conditioned synthetic image generation modules in a variety of systems. To initialize the conditional and reference branch (from a unconditional GAN)  we exploit the style mixing characteristics of high-quality GANs to generate an infinite supply of style-mixed triplets to perform the knowledge distillation. Extensive experimental results in a number of image generation tasks (i.e., image-to-image, semantic segmentation-to-image, text-to-image and audio-to-image) demonstrate qualitatively and quantitatively that our method successfully transfers knowledge to the synthetic image generation modules, resulting in more realistic images than previous methods as confirmed by a significant drop in the FID.