DynaGAN: Dynamic Few-shot Adaptation of GANs to Multiple Domains

11/26/2022
by   Seongtae Kim, et al.
0

Few-shot domain adaptation to multiple domains aims to learn a complex image distribution across multiple domains from a few training images. A naïve solution here is to train a separate model for each domain using few-shot domain adaptation methods. Unfortunately, this approach mandates linearly-scaled computational resources both in memory and computation time and, more importantly, such separate models cannot exploit the shared knowledge between target domains. In this paper, we propose DynaGAN, a novel few-shot domain-adaptation method for multiple target domains. DynaGAN has an adaptation module, which is a hyper-network that dynamically adapts a pretrained GAN model into the multiple target domains. Hence, we can fully exploit the shared knowledge across target domains and avoid the linearly-scaled computational requirements. As it is still computationally challenging to adapt a large-size GAN model, we design our adaptation module light-weight using the rank-1 tensor decomposition. Lastly, we propose a contrastive-adaptation loss suitable for multi-domain few-shot adaptation. We validate the effectiveness of our method through extensive qualitative and quantitative evaluations.

READ FULL TEXT

page 1

page 3

page 5

page 6

page 7

research
09/25/2021

Multi-source Few-shot Domain Adaptation

Multi-source Domain Adaptation (MDA) aims to transfer predictive models ...
research
08/18/2023

Smoothness Similarity Regularization for Few-Shot GAN Adaptation

The task of few-shot GAN adaptation aims to adapt a pre-trained GAN mode...
research
01/29/2021

Few-Shot Domain Adaptation for Grammatical Error Correction via Meta-Learning

Most existing Grammatical Error Correction (GEC) methods based on sequen...
research
03/14/2022

ADAS: A Direct Adaptation Strategy for Multi-Target Domain Adaptive Semantic Segmentation

In this paper, we present a direct adaptation strategy (ADAS), which aim...
research
10/22/2020

Few-Shot Adaptation of Generative Adversarial Networks

Generative Adversarial Networks (GANs) have shown remarkable performance...
research
09/12/2023

HAMUR: Hyper Adapter for Multi-Domain Recommendation

Multi-Domain Recommendation (MDR) has gained significant attention in re...
research
06/12/2021

Provable Adaptation across Multiway Domains via Representation Learning

This paper studies zero-shot domain adaptation where each domain is inde...

Please sign up or login with your details

Forgot password? Click here to reset