DEff-GAN: Diverse Attribute Transfer for Few-Shot Image Synthesis
This work addresses data scarcity in GAN training for image synthesis, offering a domain-specific solution that is incremental in nature.
The paper tackles the problem of data-efficient image synthesis by extending single-image GAN methods to model multiple images, generating diverse samples from a few input images with excellent results when similarities exist between them.
Requirements of large amounts of data is a difficulty in training many GANs. Data efficient GANs involve fitting a generators continuous target distribution with a limited discrete set of data samples, which is a difficult task. Single image methods have focused on modeling the internal distribution of a single image and generating its samples. While single image methods can synthesize image samples with diversity, they do not model multiple images or capture the inherent relationship possible between two images. Given only a handful of images, we are interested in generating samples and exploiting the commonalities in the input images. In this work, we extend the single-image GAN method to model multiple images for sample synthesis. We modify the discriminator with an auxiliary classifier branch, which helps to generate a wide variety of samples and to classify the input labels. Our Data-Efficient GAN (DEff-GAN) generates excellent results when similarities and correspondences can be drawn between the input images or classes.