LCAM: Low-Complexity Attention Module for Lightweight Face Recognition Networks

Seng Chun Hoo, Haidi Ibrahim (), Shahrel Azmin Suandi and Theam Foo Ng
Additional contact information
Seng Chun Hoo: School of Electrical & Electronic Engineering, Engineering Campus, Universiti Sains Malaysia, Nibong Tebal 14300, Pulau Pinang, Malaysia
Haidi Ibrahim: School of Electrical & Electronic Engineering, Engineering Campus, Universiti Sains Malaysia, Nibong Tebal 14300, Pulau Pinang, Malaysia
Shahrel Azmin Suandi: School of Electrical & Electronic Engineering, Engineering Campus, Universiti Sains Malaysia, Nibong Tebal 14300, Pulau Pinang, Malaysia
Theam Foo Ng: Centre of Global Sustainability Studies, Level 5, Hamzah Sendut Library, Universiti Sains Malaysia, Minden 11800, Pulau Pinang, Malaysia

Mathematics, 2023, vol. 11, issue 7, 1-27

Abstract: Inspired by the human visual system to concentrate on the important region of a scene, attention modules recalibrate the weights of either the channel features alone or along with spatial features to prioritize informative regions while suppressing unimportant information. However, the floating-point operations (FLOPs) and parameter counts are considerably high when one is incorporating these modules, especially for those with both channel and spatial attentions in a baseline model. Despite the success of attention modules in general ImageNet classification tasks, emphasis should be given to incorporating these modules in face recognition tasks. Hence, a novel attention mechanism with three parallel branches known as the Low-Complexity Attention Module (LCAM) is proposed. Note that there is only one convolution operation for each branch. Therefore, the LCAM is lightweight, yet it is still able to achieve a better performance. Experiments from face verification tasks indicate that LCAM achieves similar or even better results compared with those of previous modules that incorporate both channel and spatial attentions. Moreover, compared to the baseline model with no attention modules, LCAM achieves performance values of 0.84% on ConvFaceNeXt, 1.15% on MobileFaceNet, and 0.86% on ProxylessFaceNAS with respect to the average accuracy of seven image-based face recognition datasets.

Keywords: attention module; channel attention; spatial attention; low-complexity attention module; face verification (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/11/7/1694/pdf (application/pdf)
https://www.mdpi.com/2227-7390/11/7/1694/ (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:11:y:2023:i:7:p:1694-:d:1113831

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 ().