MSKFaceNet: A Lightweight Face Recognition Neural Network for Low-Power Devices

• Published in: IEEE access Vol. 13; pp. 120533 - 120546
• Main Authors: Zhang, Peng, Ma, Qinghua, Li, Yi, Cui, Min
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2025; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Accuracy; Artificial neural networks; attendance machine; Computational efficiency; Convolutional codes; Convolutional neural networks; Electronic devices; Embedded systems; Face recognition; Kernel; lightweight; local features; Modules; multi-scale; Neural networks; Parameterization; Performance evaluation; Power management; Real time; Real-time systems; Time and attendance systems; Transformers

In recent years, the rapid development of lightweight convolutional neural networks (CNNs) and lightweight vision transformers (ViTs) has led to significant progress in the field of mobile computing. However, deploying facial recognition models on low-power devices (with power consumption below 10 w...