Multibranch Attention Mechanism Based on Channel and Spatial Attention Fusion

Guojun Mao, Guanyi Liao, Hengliang Zhu and Bo Sun ()
Additional contact information
Guojun Mao: Fujian Provincial Key Laboratory of Big Data Mining and Applications, Fujian University of Technology, Fuzhou 350118, China
Guanyi Liao: School of Computer and Mathematics, Fujian University of Technology, Fuzhou 350118, China
Hengliang Zhu: School of Computer and Mathematics, Fujian University of Technology, Fuzhou 350118, China
Bo Sun: School of Computer and Mathematics, Fujian University of Technology, Fuzhou 350118, China

Mathematics, 2022, vol. 10, issue 21, 1-17

Abstract: Recently, it has been demonstrated that the performance of an object detection network can be improved by embedding an attention module into it. In this work, we propose a lightweight and effective attention mechanism named multibranch attention (M3Att). For the input feature map, our M3Att first uses the grouped convolutional layer with a pyramid structure for feature extraction, and then calculates channel attention and spatial attention simultaneously and fuses them to obtain more complementary features. It is a “plug and play” module that can be easily added to the object detection network and significantly improves the performance of the object detection network with a small increase in parameters. We demonstrate the effectiveness of M3Att on various challenging object detection tasks, including PASCAL VOC2007, PASCAL VOC2012, KITTI, and Zhanjiang Underwater Robot Competition. The experimental results show that this method dramatically improves the object detection effect, especially for the PASCAL VOC2007, and the mapping index of the original network increased by 4.93% when embedded in the YOLOV4 (You Only Look Once v4) network.

Keywords: object detection; multiscale module; spatial attention; channel attention; spatial attention; multibranch structure (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2022
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/10/21/4150/pdf (application/pdf)
https://www.mdpi.com/2227-7390/10/21/4150/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:10:y:2022:i:21:p:4150-:d:964842

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().