Poster: Lightweight Features Sharing for Real-Time Object Detection in Cooperative Driving

Hawlader, Faisal; Robinet, François; Frank, Raphaël

Reference : Poster: Lightweight Features Sharing for Real-Time Object Detection in Cooperative Driving


	Document type :	Scientific congresses, symposiums and conference proceedings : Paper published in a book
	Discipline(s) :	Engineering, computing & technology : Computer science
	To cite this reference:	http://hdl.handle.net/10993/54850

Title :	Poster: Lightweight Features Sharing for Real-Time Object Detection in Cooperative Driving
Language :	English
Author, co-author :	Hawlader, Faisal [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > PI Engel >]
	Robinet, François [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > SEDAN >]
	Frank, Raphaël [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > SEDAN >]
Publication date :	26-Apr-2023
Main document title :	2023 IEEE Vehicular Networking Conference (VNC)
Peer reviewed :	Yes
Event name :	2023 IEEE Vehicular Networking Conference (VNC)
Event date :	26-04-2023 to 28-04-2023
Event place (city) :	Istanbul
Event country :	Türkiye
Keywords :	[en] Real-time Object Detection ; Neural Network Quantization ; Model Compression ; V2X Communication
Abstract :	[en] In model partitioning for real-time object detection, part of the model is deployed on a vehicle, and the remaining layers are processed in the cloud. Model partitioning requires transmitting intermediate features to the cloud, which can be problematic, given that the latency requirements are strict. This paper addresses this issue by demonstrating a lightweight featuresharing strategy while investigating a trade-off between detection quality and latency. We report details on layer partitioning, such as which layers to split in order to achieve the desired accuracy.
Target :	Researchers ; Professionals ; Students ; General public ; Others
Permalink :	http://hdl.handle.net/10993/54850

File(s) associated to this reference

Fulltext file(s):

	File	Commentary	Version	Size	Access
Limited access	main.pdf		Author preprint	164.77 kB	Request a copy

All documents in ORBi^lu are protected by a user license.

University of Luxembourg Library | Feedback | Legal notices