BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Generalization vs Specialization in Computer Vision for Ecology - 
 Assoc Prof Sara Beery\, Faculty of Artificial Intelligence and Decision-Ma
 king\, CSAIL\, MIT
DTSTART:20240130T160000Z
DTEND:20240130T170000Z
UID:TALK209701@talks.cam.ac.uk
CONTACT:Annabelle Scott
DESCRIPTION:There are explicit tradeoffs between generality and specificit
 y in computer vision methods with respect to designing impactful end-to-en
 d solutions for ecological challenges — computer vision systems that are
  general purpose but optimal for each stakeholder\, taking into account co
 st\, human effort\, and risk. We explore these tradeoffs across several di
 mensions\, investigating the impact of generality vs specificity with rega
 rds to data\, labels\, tasks\, and models\, and propose joint compression 
 and specialization of large generalist models as an efficient and cost-eff
 ective alternative to retraining or fine tuning in resource-constrained sc
 enarios such as remote field-based ecological monitoring.
LOCATION:Drum Building\, Madingley Rise Site\, West Cambridge and on zoom:
   https://zoom.us/j/6708259482?pwd=Qk03U3hxZWNJZUZpT2pVZnFtU2RRUT09
END:VEVENT
END:VCALENDAR