Supplementary for ICIP rebuttal
Year: 2025
Type: supplementary-materials
Abstract: This paper presents FaceLiVT, a lightweight yet powerful face recognition model that combines a hybrid CNN-Transformer architecture with an innovative and lightweight Multi-Head Linear Attention (MHLA) mechanism. By incorporating MHLA alongside a reparameterized token mixer, FaceLiVT effectively reduces computational complexity while preserving high accuracy. Extensive evaluations on challenging benchmarks—including LFW, CFP-FP, AgeDB-30, IJB-B, and IJB-C—highlight its superior performance compared to state-of-the-art lightweight models. The integration of MHLA significantly enhances inference speed, enabling FaceLiVT to achieve competitive accuracy with lower latency on mobile devices. Notably, FaceLiVT is 8.6×faster than EdgeFace, a recent hybrid CNN-Transformer model optimized for edge devices. With its balanced design, FaceLiVT provides a practical and efficient solution for real-time face recognition on resource-constrained platforms.
Source: IEEE SIGPORT
DOI: 10.60864/2dda-yx65
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W6958891669
Cites:
Cited by:
Related to: