DeltaGAN: Towards Diverse Few-shot Image Generation with Sample-Specific Delta

Abstract

Learning to generate new images for a novel category based on only a few images, named as few-shot image generation, has attracted increasing research interest. Several state-of-the-art works have yielded impressive results, but the diversity is still limited. In this work, we propose a novel Delta Generative Adversarial Network (DeltaGAN), which consists of a reconstruction subnetwork and a generation subnetwork. The reconstruction subnetwork captures intra-category transformation, i.e., delta, between same-category pairs. The generation subnetwork generates sample-specific delta for an input image, which is combined with this input image to generate a new image within the same category. Besides, an adversarial delta matching loss is designed to link the above two subnetworks together. Extensive experiments on six benchmark datasets demonstrate the effectiveness of our proposed method. Our code is available at https://github.com/bcmi/DeltaGAN-Few-Shot-Image-Generation.

I want to withdraw this version and use it to update the previous version at arXiv:2009.08753

References in corpus (10)

• Conditional Generative Adversarial Nets
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• The Effectiveness of Data Augmentation in Image Classification using Deep Learning
• EMNIST: an extension of MNIST to handwritten letters
• Variational Autoencoder for Deep Learning of Images, Labels and Captions
• Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules
• FIGR: Few-shot Image Generation with Reptile
• PixelGAN Autoencoders
• DAWSON: A Domain Adaptive Few Shot Generation Framework
• Meta-Reinforced Synthetic Data for One-Shot Fine-Grained Visual Recognition