F2GAN: Fusing-and-Filling GAN for Few-shot Image Generation
arXiv:2008.01999
Abstract
In order to generate images for a given category, existing deep generative models generally rely on abundant training images. However, extensive data acquisition is expensive and fast learning ability from limited data is necessarily required in real-world applications. Also, these existing methods are not well-suited for fast adaptation to a new category. Few-shot image generation, aiming to generate images from only a few images for a new category, has attracted some research interest. In this paper, we propose a Fusing-and-Filling Generative Adversarial Network (F2GAN) to generate realistic and diverse images for a new category with only a few images. In our F2GAN, a fusion generator is designed to fuse the high-level features of conditional images with random interpolation coefficients, and then fills in attended low-level details with non-local attention module to produce a new image. Moreover, our discriminator can ensure the diversity of generated images by a mode seeking loss and an interpolation regression loss. Extensive experiments on five datasets demonstrate the effectiveness of our proposed method for few-shot image generation.
This paper is accepted by ACM Multimedia 2020
References in corpus (6)
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- EMNIST: an extension of MNIST to handwritten letters
- Variational Autoencoder for Deep Learning of Images, Labels and Captions
- FIGR: Few-shot Image Generation with Reptile
- Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis
- DAWSON: A Domain Adaptive Few Shot Generation Framework