BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Chicago
X-LIC-LOCATION:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20230124T171522Z
LOCATION:C144-145
DTSTART;TZID=America/Chicago:20221114T145000
DTEND;TZID=America/Chicago:20221114T150000
UID:submissions.supercomputing.org_SC22_sess462_ws_ai4s110@linklings.com
SUMMARY:Determining HEDP Foams' Quality with Multi-View Deep Learning Clas
 sification
DESCRIPTION:Workshop\n\nDetermining HEDP Foams' Quality with Multi-View De
 ep Learning Classification\n\nSchneider, Rusanovsky, Gvishi, Oren\n\nHEDP 
 experiments commonly involve a dynamic wave-front propagating inside a low
 -density foam. To classify the foams' quality, accurate information is req
 uired. For each foam, five images are taken: two 2D images representing th
 e top and bottom surface foam planes and three images of side cross-sectio
 ns from 3D scannings. An expert has to do the complicated, harsh, and exha
 usting work of manually classifying the foam's quality through the image s
 et and only then determine whether the foam can be used in experiments or 
 not. In this work, we present a novel state-of-the-art multi-view deep-lea
 rning classification model determining the foams' quality classification a
 nd thus aids the expert. Our model achieved 86% accuracy on upper and lowe
 r surface foam planes and 82% on the entire set, suggesting interesting he
 uristics to the problem. A significant added value in this work is the abi
 lity to regress the foam quality and even explain the decision visually.\n
 \nSession Format: Recorded\n\nRegistration Category: Workshop Reg Pass
END:VEVENT
END:VCALENDAR