2 papers
cs.CV2025
FaceLiVT: Face Recognition using Linear Vision Transformer with Structural Reparameterization For Mobile Device
Novendra Setyawan, Chi-Chia Sun, Mao-Hsiu Hsu +2
This paper introduces FaceLiVT, a lightweight yet powerful face recognition model that integrates a hybrid Convolution Neural Network (CNN)-Transformer architecture with an innovat…
cs.CV2025
MicroViT: A Vision Transformer with Low Complexity Self Attention for Edge Device
Novendra Setyawan, Chi-Chia Sun, Mao-Hsiu Hsu +2
The Vision Transformer (ViT) has demonstrated state-of-the-art performance in various computer vision tasks, but its high computational demands make it impractical for edge devices…