A Lightweight YOLOv2 Object Detector Using a Dilated Convolution

Tuan Nghia Nguyen, Xuan Truong Nguyen, Hyun Kim, Hyuk Jae Lee

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

In recent years, object detection approaches such as you-only-look-once (YOLO) have been getting a special attention owing to the emerging trend of autonomous driving systems. However, memory and computation complexity are usually known as the bottlenecks in implementing a YOLOv2 in hardware design. This study proposes a simple yet effective variant of YOLOv2 by using dilated convolution to reduce its complexity. Experimental results show that the proposed method achieves up to 36% of memory access reduction and 9% of computation reduction on a network with a negligible performance loss of 1.75% on the well-known VOC dataset.

Original languageEnglish
Title of host publication34th International Technical Conference on Circuits/Systems, Computers and Communications, ITC-CSCC 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728132716
DOIs
StatePublished - Jun 2019
Event34th International Technical Conference on Circuits/Systems, Computers and Communications, ITC-CSCC 2019 - JeJu, Korea, Republic of
Duration: 23 Jun 201926 Jun 2019

Publication series

Name34th International Technical Conference on Circuits/Systems, Computers and Communications, ITC-CSCC 2019

Conference

Conference34th International Technical Conference on Circuits/Systems, Computers and Communications, ITC-CSCC 2019
Country/TerritoryKorea, Republic of
CityJeJu
Period23/06/1926/06/19

Keywords

  • dilated convolution
  • YOLOv2

Fingerprint

Dive into the research topics of 'A Lightweight YOLOv2 Object Detector Using a Dilated Convolution'. Together they form a unique fingerprint.

Cite this