BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:TEGLIE: Transformer Encoders as strong Gravitational Lens finders 
 In the Kilo DegreE Survey
DTSTART;VALUE=DATE-TIME:20240606T071500Z
DTEND;VALUE=DATE-TIME:20240606T081500Z
DTSTAMP;VALUE=DATE-TIME:20260813T144950Z
UID:indico-contribution-1556@events.ncbj.gov.pl
DESCRIPTION:Speakers: Margherita Grespan (NCBJ)\nIn this seminar\, I will 
 explore the potential of Transformer Encoders in detecting strong gravitat
 ional lenses (SGLs) within wide-area surveys. This study focuses on the Ki
 lo Degree Survey (KiDS) as the primary dataset. Initially\, the model was 
 trained on simulated data from the Bologna Lens Challenge\, designed to cl
 osely mimic actual KiDS observations. Following this\, the model was refin
 ed through fine-tuning and data augmentation using real KiDS data\, which 
 included images of previously identified SGL candidates and non-lens examp
 les. This refinement led to a substantial 70% reduction in false positives
 \, although the precision remained lower than 1%.\nThis approach resulted 
 in a catalog of 263 SGL candidates\, of which 43 are newly discovered high
 -confidence SGLs. This seminar will highlight the difficulties in detectin
 g rare objects such as gravitational lenses and the challenges to overcome
  to be ready for the next generation of wide-area surveys.\n\nhttps://even
 ts.ncbj.gov.pl/event/300/contributions/1556/
LOCATION:NCBJ Room 207
URL:https://events.ncbj.gov.pl/event/300/contributions/1556/
END:VEVENT
END:VCALENDAR
