BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Embed2Scale - ECPv6.15.20//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://embed2scale.eu
X-WR-CALDESC:Events for Embed2Scale
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:UTC
BEGIN:STANDARD
TZOFFSETFROM:+0000
TZOFFSETTO:+0000
TZNAME:UTC
DTSTART:20250101T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=UTC:20260327T150000
DTEND;TZID=UTC:20260327T160000
DTSTAMP:20260603T215952
CREATED:20260212T160757Z
LAST-MODIFIED:20260331T093601Z
UID:10000023-1774623600-1774627200@embed2scale.eu
SUMMARY:Webinar: "Visual Prompting for Geospatial Image Segmentation based on Embedding Maps"
DESCRIPTION:Home » Event\n\n\n\n\n\n\n\n\n\n\n\n\nSPIE Security + Defence\n\n\n\n\n\n\n\n\nThe application of Foundation Models to Earth Observation (EO) data is often slowed down by complex data preparation for fine-tuning\, creating the need for more efficient adaptation strategies.  \n\n\n\nThis webinar 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)\, the segmentation mask is created based on similarity scores between prompt and image embeddings. \n\n\n\nThe webinar showcases a working prototype demonstration\, explains its functionality and opens the discussion on future work. \n\n\n\nWatch the webinar
URL:https://embed2scale.eu/event/visual-prompting-for-geospatial-image-segmentation-based-on-embedding-maps/
CATEGORIES:Event
ATTACH;FMTTYPE=image/jpeg:https://embed2scale.eu/wp-content/uploads/2026/02/Visual-Prompting-for-Geospatial-Image-Segmentation-based-on-Embedding-Maps_Web.jpg
END:VEVENT
END:VCALENDAR