A Closer Look at Few-shot Image Generation

05/08/2022
by   Yunqing Zhao, et al.
0

Modern GANs excel at generating high quality and diverse images. However, when transferring the pretrained GANs on small target data (e.g., 10-shot), the generator tends to replicate the training samples. Several methods have been proposed to address this few-shot image generation task, but there is a lack of effort to analyze them under a unified framework. As our first contribution, we propose a framework to analyze existing methods during the adaptation. Our analysis discovers that while some methods have disproportionate focus on diversity preserving which impede quality improvement, all methods achieve similar quality after convergence. Therefore, the better methods are those that can slow down diversity degradation. Furthermore, our analysis reveals that there is still plenty of room to further slow down diversity degradation. Informed by our analysis and to slow down the diversity degradation of the target generator during adaptation, our second contribution proposes to apply mutual information (MI) maximization to retain the source domain's rich multi-level diversity information in the target domain generator. We propose to perform MI maximization by contrastive loss (CL), leverage the generator and discriminator as two feature encoders to extract different multi-level features for computing CL. We refer to our method as Dual Contrastive Learning (DCL). Extensive experiments on several public datasets show that, while leading to a slower diversity-degrading generator during adaptation, our proposed DCL brings visually pleasant quality and state-of-the-art quantitative performance.

READ FULL TEXT

page 1

page 7

page 8

research
10/27/2022

Few-shot Image Generation via Masked Discrimination

Few-shot image generation aims to generate images of high quality and gr...
research
05/12/2022

D3T-GAN: Data-Dependent Domain Transfer GANs for Few-shot Image Generation

As an important and challenging problem, few-shot image generation aims ...
research
12/04/2020

Few-shot Image Generation with Elastic Weight Consolidation

Few-shot image generation seeks to generate more data of a given domain,...
research
11/07/2022

Few-shot Image Generation with Diffusion Models

Denoising diffusion probabilistic models (DDPMs) have been proven capabl...
research
07/04/2023

AdAM: Few-Shot Image Generation via Adaptation-Aware Kernel Modulation

Few-shot image generation (FSIG) aims to learn to generate new and diver...
research
08/21/2023

Improving Diversity in Zero-Shot GAN Adaptation with Semantic Variations

Training deep generative models usually requires a large amount of data....
research
03/16/2022

CtlGAN: Few-shot Artistic Portraits Generation with Contrastive Transfer Learning

Generating artistic portraits is a challenging problem in computer visio...

Please sign up or login with your details

Forgot password? Click here to reset