Seongtae Kim
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Seongtae Kim has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Geonung Kim
POSTECH, Pohang, Republic of Korea
1 shared publication - Kyoungkook Kang
Samsung, Suwon, Republic of Korea
1 shared publication - Seung-Hwan Baek
POSTECH, Pohang, Republic of Korea
1 shared publication - Sunghyun Cho
POSTECH, Pohang, Republic of Korea
1 shared publication
Latest Publications
- Open Access
- 29 November 2022
- Published by Association for Computing Machinery (ACM)
- p. 1-8
DynaGAN: Dynamic Few-shot Adaptation of GANs to Multiple Domains
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 to be lightweight 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.
- 29 November 2022
- Published by Association for Computing Machinery (ACM)
- p. 1-8
Open AccessDynaGAN: Dynamic Few-shot Adaptation of GANs to Multiple Domains
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 to be lightweight 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.