BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Imaging Lunch: Segment-Anything Model (SAM): A Foundation Model fo
 r Object Segmentation and Tracking
DTSTART:20260225T110000
DTEND:20260225T130000
DTSTAMP:20260415T075938Z
UID:9968e6fc46d1abadff386e4c0f248f4d23d5ac685c9f23316099c784
CATEGORIES:Conferences - Seminars
DESCRIPTION:Pablo Garcia-Amorena\, Daniel Sage\nRegistration\n\nAbstract\n
 \nVision transformers are powering a “ChatGPT moment” for image segmen
 tation: instead of tedious manual outlining\, you can steer a model with a
  few clicks or a short prompt and get usable masks in seconds. In this wor
 kshop\, we will show how to turn today’s foundation model tools into a p
 ractical\, repeatable workflow that fits real imaging projects\, from quic
 k measurements to scalable annotation.\n\nAfter a short\, intuition-first 
 overview of segmentation using vision transformers and how these models re
 spond to prompts\, we will jump into hands-on demos with the latest Meta S
 egment Anything Models (SAM\, including models SAM2 and SAM3) to segment\,
  refine\, and propagate masks across image series/video-like data. We will
  also cover streamlined workflows for dataset creation and user-assisted a
 nnotation\, plus tips that improve speed and consistency on challenging bo
 undaries and large images.\nFinally\, we will focus on recognizing common 
 failure modes\, validating results\, and documenting prompts and settings 
 so segmentations stay reliable and reproducible.\n\nLearning Objectives\n\
 n	Use segmentation using foundation models (SAM2/SAM3) to produce and refi
 ne masks from clicks/boxes and concept prompts.\n	 \n	Apply efficient wor
 kflows for different production needs: single images\, propagation across 
 series/video\, and rapid dataset annotation.\n	 \n	Assess of quality outp
 uts: spot typical failure modes\, run quick validation checks and reproduc
 ible results.\n	 \n\nPrerequisites\n\n\n	Intermediate: comfortable workin
 g with scientific images and basic file handling\n	 \n	Basic Python skill
 s (e.g.\, running notebooks/scripts\, installing packages\n	 \n	Laptop re
 commended if you want to follow along hands-o\n\n\nAbout the Imaging Lunch
 es: \nOnce per month\, the EPFL Center for Imaging organises an event ded
 icated to all PhD students and postdocs working with/in imaging. Discuss t
 he latest advances in imaging. Connect with imaging peers. Learn about pop
 ular imaging tools!\n\n 
LOCATION:BC 410 https://plan.epfl.ch/?room==BC%20410
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR