BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Seoul
X-LIC-LOCATION:Asia/Seoul
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:KST
DTSTART:18871231T000000
DTSTART:19881009T020000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20230103T035307Z
LOCATION:Room 325-AB\, Level 3\, West Wing
DTSTART;TZID=Asia/Seoul:20221206T153000
DTEND;TZID=Asia/Seoul:20221206T170000
UID:siggraphasia_SIGGRAPH Asia 2022_sess157_papers_487@linklings.com
SUMMARY:DynaGAN: Dynamic Few-shot Adaptation of GANs to Multiple Domains
DESCRIPTION:Technical Communications, Technical Papers\n\nDynaGAN: Dynamic
  Few-shot Adaptation of GANs to Multiple Domains\n\nKim, Kang, Kim, Baek, 
 Cho\n\nFew-shot domain adaptation to multiple domains aims to learn a comp
 lex image distribution across multiple domains from a few training images.
  A naive 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 tim
 e and, more importantly, such separate models cannot exploit the shared kn
 owledge between target domains. In this paper, we propose DynaGAN, a novel
  few-shot domain-adaptation method for multiple target domains. DynaGAN ha
 s an adaptation module, which is a hyper-network that dynamically adapts a
  pretrained GAN model into the multiple target domains. Hence, we can full
 y exploit the shared knowledge across target domains and avoid the linearl
 y-scaled computational requirements. As it is still computationally challe
 nging 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 qualitativ
 e and quantitative evaluations.\n\nRegistration Category: FULL ACCESS, ON-
 DEMAND ACCESS\n\nLanguage: ENGLISH\n\nFormat: IN-PERSON, ON-DEMAND
URL:https://sa2022.siggraph.org/en/full-program/?id=papers_487&sess=sess15
 7
END:VEVENT
END:VCALENDAR