Esther Robb, Jia-Bin Huang

Abstract

Generative Adversarial Networks (GANs) have shown remarkable performance in image synthesis tasks, but typically require a large number of training samples to achieve high-quality synthesis. This paper proposes a simple and effective method, Few-Shot GAN (FSGAN), for adapting GANs in few-shot settings (less than 100 images). FSGAN repurposes component analysis techniques and learns to adapt the singular values of the pre-trained weights while freezing the corresponding singular vectors. This provides a highly expressive parameter space for adaptation while constraining changes to the pretrained weights. We validate our method in a challenging few-shot setting of 5-100 images in the target domain. We show that our method has significant visual quality gains compared with existing GAN adaptation methods. We report qualitative and quantitative results showing the effectiveness of our method. We additionally highlight a problem for few-shot synthesis in the standard quantitative metric used by data-efficient image synthesis works.

People

Jia-Bin Huang


Esther Robb


Publication Details

Date of publication:
October 22, 2020
Journal:
Cornell University
Publication note:

Esther Robb, Wen-Sheng Chu, Abhishek Kumar, Jia-Bin Huang: Few-Shot Adaptation of Generative Adversarial Networks. CoRR abs/2010.11943 (2020)