MatchingGAN: Matching-based Few-shot Image Generation

Abstract

To generate new images for a given category, most deep generative models require abundant training images from this category, which are often too expensive to acquire. To achieve the goal of generation based on only a few images, we propose matching-based Generative Adversarial Network (GAN) for few-shot generation, which includes a matching generator and a matching discriminator. Matching generator can match random vectors with a few conditional images from the same category and generate new images for this category based on the fused features. The matching discriminator extends conventional GAN discriminator by matching the feature of generated image with the fused feature of conditional images. Extensive experiments on three datasets demonstrate the effectiveness of our proposed method.

This paper is accepted for oral presentation at ICME 2020(http://www.2020.ieeeicme.org/)

References in corpus (11)

• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Spectral Normalization for Generative Adversarial Networks
• Conditional Image Synthesis With Auxiliary Classifier GANs
• Which Training Methods for GANs do actually Converge?
• Data Augmentation Generative Adversarial Networks
• On First-Order Meta-Learning Algorithms
• EMNIST: an extension of MNIST to handwritten letters
• One-shot Learning with Memory-Augmented Neural Networks
• Delta-encoder: an effective sample synthesis method for few-shot object recognition
• An empirical study on evaluation metrics of generative adversarial networks
• FIGR: Few-shot Image Generation with Reptile