Generalized One-shot Domain Adaption of Generative Adversarial Networks

by   Zicheng Zhang, et al.

The adaption of Generative Adversarial Network (GAN) aims to transfer a pre-trained GAN to a given domain with limited training data. In this paper, we focus on the one-shot case, which is more challenging and rarely explored in previous works. We consider that the adaptation from source domain to target domain can be decoupled into two parts: the transfer of global style like texture and color, and the emergence of new entities that do not belong to the source domain. While previous works mainly focus on the style transfer, we propose a novel and concise framework[<>] to address the generalized one-shot adaption task for both style and entity transfer, in which a reference image and its binary entity mask are provided. Our core objective is to constrain the gap between the internal distributions of the reference and syntheses by sliced Wasserstein distance. To better achieve it, style fixation is used at first to roughly obtain the exemplary style, and an auxiliary network is introduced to the original generator to disentangle entity and style transfer. Besides, to realize cross-domain correspondence, we propose the variational Laplacian regularization to constrain the smoothness of the adapted generator. Both quantitative and qualitative experiments demonstrate the effectiveness of our method in various scenarios.


page 1

page 4

page 6

page 8

page 9


Towards Diverse and Faithful One-shot Adaption of Generative Adversarial Networks

One-shot generative domain adaption aims to transfer a pre-trained gener...

Domain Adaptation for Learning Generator from Paired Few-Shot Data

We propose a Paired Few-shot GAN (PFS-GAN) model for learning generators...

Exploiting Style Transfer-based Task Augmentation for Cross-Domain Few-Shot Learning

In cross-domain few-shot learning, the core issue is that the model trai...

CIT-GAN: Cyclic Image Translation Generative Adversarial Network With Application in Iris Presentation Attack Detection

In this work, we propose a novel Cyclic Image Translation Generative Adv...

Mind the Gap: Domain Gap Control for Single Shot Domain Adaptation for Generative Adversarial Networks

We present a new method for one shot domain adaptation. The input to our...

Stain Style Transfer of Histopathology Images Via Structure-Preserved Generative Learning

Computational histopathology image diagnosis becomes increasingly popula...

Few-Shot Domain Expansion for Face Anti-Spoofing

Face anti-spoofing (FAS) is an indispensable and widely used module in f...

Please sign up or login with your details

Forgot password? Click here to reset