BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
X-LIC-LOCATION:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20211208T164413Z
LOCATION:3016
DTSTART;TZID=America/Los_Angeles:20211209T141000
DTEND;TZID=America/Los_Angeles:20211209T143000
UID:dac_DAC 2021_sess102_RESEARCH641@linklings.com
SUMMARY:Neural Pruning Search for Real-Time Object Detection of Autonomous
  Vehicles
DESCRIPTION:Research Manuscript\n\nNeural Pruning Search for Real-Time Obj
 ect Detection of Autonomous Vehicles\n\nZhao\n\nObject detection plays an 
 important role in self-driving cars. However, mobile systems on self-drivi
 ng cars with limited resources lead to difficulties for object detection. 
 To facilitate this, we propose a compiler-aware neural pruning search fram
 ework  to achieve high-speed inference on autonomous vehicles for 2D and 3
 D object detection. The framework automatically searches the pruning schem
 e and rate for each layer to find a best-suited pruning for optimizing det
 ection accuracy and speed performance under compiler optimization. Our exp
 eriments demonstrate that for the first time, the proposed method achieves
  (close-to) real-time on an off-the-shelf mobile phone with minor accuracy
  loss.\n\nTopic: Autonomous Systems\n\nVirtual Program: Presented In-Perso
 n
END:VEVENT
END:VCALENDAR