CSL-YOLO: A Cross-Stage Lightweight Object Detector with Low FLOPs

Yu Ming Zhang, Chun Chieh Lee, Jun Wei Hsieh, Kuo Chin Fan

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

2 Scopus citations

Abstract

The development of lightweight object detectors is essential due to the limited computation resources. To reduce the computation cost, how to generate features plays a significant role. This paper proposes a new lightweight convolution method Cross-Stage Lightweight Module (CSL-M). It combines the Inverted Residual Block (IRB) and Cross-Stage Partial (CSP) concept. Experiments conducted at CIFAR-10 show that the proposed CSL-Net based on CSL-M performs better with fewer FLOPs than the other lightweight backbones. Finally, we use CSL-Net as the backbone to construct a lightweight detector CSL-YOLO, achieving better detection performance with only 43% FLOPs and 52% parameters than Tiny-YOLOv4.

Original languageEnglish
Title of host publicationIEEE International Symposium on Circuits and Systems, ISCAS 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2730-2734
Number of pages5
ISBN (Electronic)9781665484855
DOIs
StatePublished - 2022
Event2022 IEEE International Symposium on Circuits and Systems, ISCAS 2022 - Austin, United States
Duration: 27 May 20221 Jun 2022

Publication series

NameProceedings - IEEE International Symposium on Circuits and Systems
Volume2022-May
ISSN (Print)0271-4310

Conference

Conference2022 IEEE International Symposium on Circuits and Systems, ISCAS 2022
Country/TerritoryUnited States
CityAustin
Period27/05/221/06/22

Keywords

  • lightweight detector
  • low FLOPs
  • MS-COCO
  • YOLO

Fingerprint

Dive into the research topics of 'CSL-YOLO: A Cross-Stage Lightweight Object Detector with Low FLOPs'. Together they form a unique fingerprint.

Cite this