Knowledge Distillation Generative Adversarial Network for Image-to-Image Translation

An Image-to-Image (I2I) translation technique is a method that transforms an image from one domain to another by mapping one domain onto another. This technique involves two generators and two discriminators. Each generator can only translate one domain to another. This paper proposes a new approach called Knowledge Distillation Generative Adversarial Network (KD-GAN). The KD-GAN uses an image generated from Cycle-Consistent Generative Adversarial Networks (CycleGAN) as part of the target in training for a new generator. Our experiment involved translating between males and females in the CelebA dataset. We compared our model's ' s results with the state-of-the-art using Fr & eacute;chet Inception Distance (FID) and Kernel Inception Distance (KID). The experiment showed that while KD-GAN is not the best regarding FID and KID, the output image can better keep the skin tone and hairstyle from the input image than other methods.