BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:Europe/Brussels
BEGIN:DAYLIGHT
DTSTART:20260329T030000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20251026T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260605T080400Z
UID:QFneXg
DTSTART;TZID=Europe/Brussels:20260327T150000
DTEND;TZID=Europe/Brussels:20260327T160000
CLASS:PUBLIC
CREATED:20260217T115927
DESCRIPTION: The application of Foundation Models to Earth Observation (EO)
  data is often slowed down by complex data preparation for fine-tuning\, c
 reating the need for more efficient adaptation strategies.  \n\n This webi
 nar features the Visual Prompting for Geospatial Image Segmentation (VP‑
 GIS)\, a framework that utilises high-dimensional embedding maps to guide 
 zero-shot segmentation models toward domain-specific features. Rather than
  modifying model weights\, the VP‑GIS approach injects learnable visual 
 prompts into the input space\, derived from the topological structures of 
 pre-computed embedding manifolds. By aligning the visual prompts with the 
 latent distribution of geospatial features (e.g.\, cosine similarity)\, th
 e segmentation mask is created based on similarity scores between prompt a
 nd image embeddings. \n\n The webinar showcases a working prototype demons
 tration\, explains its functionality and opens the discussion on future wo
 rk. \n
LAST-MODIFIED:20260217T121300
LOCATION:Online
ORGANIZER:mailto:info@embed2scale.eu
SUMMARY:Visual Prompting for Geospatial Image Segmentation based on Embeddi
 ng Maps
URL;VALUE=URI:https://ti.to/embed2scale/visual-prompting-for-geospatial-ima
 ge-segmentation-based-on-embedding-maps
URL;VALUE=URI:https://ti.to/embed2scale/visual-prompting-for-geospatial-ima
 ge-segmentation-based-on-embedding-maps
END:VEVENT
END:VCALENDAR