BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Australia/Melbourne
X-LIC-LOCATION:Australia/Melbourne
BEGIN:DAYLIGHT
TZOFFSETFROM:+1000
TZOFFSETTO:+1100
TZNAME:AEDT
DTSTART:19721003T020000
RRULE:FREQ=YEARLY;BYMONTH=4;BYDAY=1SU
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:19721003T020000
TZOFFSETFROM:+1100
TZOFFSETTO:+1000
TZNAME:AEST
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20240214T070248Z
LOCATION:Meeting Room C4.9+C4.10\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231214T144000
DTEND;TZID=Australia/Melbourne:20231214T145000
UID:siggraphasia_SIGGRAPH Asia 2023_sess132_papers_528@linklings.com
SUMMARY:Content-based Search for Deep Generative Models
DESCRIPTION:Technical Papers\n\nDaohan Lu, Sheng-Yu Wang, Nupur Kumari, Ro
 han Agarwal, and Mia Tang (Carnegie Mellon University); David Bau (Northea
 stern University); and Jun-Yan Zhu (Carnegie Mellon University)\n\nThe gro
 wing proliferation of customized and pretrained generative models has made
  it infeasible for a user to be fully cognizant of every model in existenc
 e. To address this need, we introduce the task of content-based model sear
 ch: given a query and a large set of generative models, finding the models
  that best match the query. As each generative model produces a distributi
 on of images, we formulate the search task as an optimization problem to s
 elect the model with the highest probability of generating similar content
  as the query. \nWe introduce a formulation to approximate this probabilit
 y given the query from different modalities, e.g., image, sketch, and text
 . Furthermore, we propose a contrastive learning framework for model retri
 eval, which learns to adapt features for various query modalities. We demo
 nstrate that our method outperforms several baselines on Generative Model 
 Zoo, a new benchmark we create for the model retrieval task.\n\nRegistrati
 on Category: Full Access\n\nSession Chair: Jun-Yan Zhu (Carnegie Mellon Un
 iversity)
URL:https://asia.siggraph.org/2023/full-program?id=papers_528&sess=sess132
END:VEVENT
END:VCALENDAR