A Double Stream Module in Backbone for Object Detection Network

Xuanfang He, Yan Ding, Yating Yuan, Weidong Liang, Xinliang Huang, Jiayuan Shan

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

Abstract

The representation ability of the network is crucial for object detection. In this paper, we present a novel building block named double stream block to construct a backbone called double stream module (DSM) to improve the representation ability of object detection networks. The double stream block is designed by fusing the shuffle branch and the non shuffle branch with a weight layer. To make our block adaptive for the depth of the convolutional layer, a shortcut connection is adopted after the double stream fusion. After that, DSM is built as a backbone and integrated into Faster-RCNN, Cascade-RCNN, DetectoRS detection system to verify its applicability. On the VisDrone dataset of VAV, the evaluation results for object detection show that the double stream design can significantly increase the representation ability of the network, and our approach gains 2.0, 0.5and 1.1 mAP improvements in the detection systems mentioned above respectively.

Original languageEnglish
Title of host publication2021 4th International Conference on Artificial Intelligence and Big Data, ICAIBD 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages567-571
Number of pages5
ISBN (Electronic)9780738131702
DOIs
Publication statusPublished - 28 May 2021
Event4th International Conference on Artificial Intelligence and Big Data, ICAIBD 2021 - Chengdu, China
Duration: 28 May 202131 May 2021

Publication series

Name2021 4th International Conference on Artificial Intelligence and Big Data, ICAIBD 2021

Conference

Conference4th International Conference on Artificial Intelligence and Big Data, ICAIBD 2021
Country/TerritoryChina
CityChengdu
Period28/05/2131/05/21

Keywords

  • double stream module
  • object detection

Fingerprint

Dive into the research topics of 'A Double Stream Module in Backbone for Object Detection Network'. Together they form a unique fingerprint.

Cite this