Thenwesynthesizepseudo pair images through the latent space exploration of StyleGAN2 to find implicit associations between different animal faces. Finally, we introduce the semantic matching loss to overcome the problem of extreme shape differences between species.

A large brown metal cube belowa large green rubber cylinder A large gray metal sphereabove a small red metal cube A small red metal cube behinda large brown metal cube A large brown metal cube below a large green rubber cylinder A large gray metal sphereabove a small red metal cube A small red metal cube on the left of a large brown metal cube A large brown metal cube below a large green rubber cylinder A blue objectinfrontofa gray object! A gray object on the left ofa green object A green object behindablue object! A blue objectin front ofa gray object! A gray object behind a green object! A green object on the left ofa blue object! A blue object behind a gray object A gray object on the left ofa green object A green object on the right ofa gray object CLIPQuery imageFine-tuned CLIPOurs( a) Top 1 image-text retrieval result on i Gibsonscenes.(

Generative adversarial networks (GANs) typically require ample data for training in order to synthesize high-fidelity images.

(iteration 2).

Big data has enabled deep learning algorithms achieve rapid advancements. In particular, stateof-the-art generative adversarial networks (GANs) [11] are able to generate high-fidelity natural images of diverse categories [2,18]. Many computer vision and graphics applications have been enabled[32,43,53].