paper-with-me

Papers

FaceLiVT: Face Recognition using Linear Vision Transformer with Structural Reparameterization For Mobile Device

2025-06-12 · Novendra Setyawan, Chi-Chia Sun, Mao-Hsiu Hsu, Wen-Kai Kuo, Jun-Wei Hsieh

This paper introduces FaceLiVT, a lightweight yet powerful face recognition model that integrates a hybrid Convolution Neural Network (CNN)-Transformer architecture with an innovative and lightweight Multi-Head Linear Attention (MHLA) mechanism. By combining MHLA alongside a reparameterized token mixer, FaceLiVT effectively reduces computational complexity while preserving competitive 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. MHLA notably improves inference speed, allowing FaceLiVT to deliver high accuracy with lower latency on mobile devices. Specifically, FaceLiVT is 8.6 faster than EdgeFace, a recent hybrid CNN-Transformer model optimized for edge devices, and 21.2 faster than a pure ViT-Based model. With its balanced design, FaceLiVT offers an efficient and practical solution for real-time face recognition on resource-constrained platforms.

📄 PDF Abstract BibTeX arXiv:2506.10361

Code (0)

등록된 구현이 없습니다.

Tasks

Face Recognition

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Multi-Head Linear Attention Multi-Head Linear Attention is a type of linear multi-head self-attention module, proposed with the Linformer architecture. The…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

FaceLiVTv2: An Improved Hybrid Architecture for Efficient Mobile Face Recognition

2026-04-10 · Novendra Setyawan, Chi-Chia Sun, Mao-Hsiu Hsu, Wen-Kai Kuo 외 arxiv

Lightweight face recognition is increasingly important for deployment on edge and mobile devices, where strict constraints on latency, memory, and energy consumption must be met alongside reliable accuracy. Although rece…

Lightweight Face RecognitionComputational Efficiency

Part-based Face Recognition with Vision Transformers

2022-11-30 · Zhonglin Sun, Georgios Tzimiropoulos

Holistic methods using CNNs and margin-based losses have dominated research on face recognition. In this work, we depart from this setting in two ways: (a) we employ the Vision Transformer as an architecture for training…

Face Recognition

Data-Efficient Realized Volatility Forecasting with Vision Transformers

2025-11-04 · Emi Soroka, Artem Arzyn arxiv

Recent work in financial machine learning has shown the virtue of complexity: the phenomenon by which deep learning methods capable of learning highly nonlinear relationships outperform simpler approaches in financial fo…

Time Series Forecasting

Face Transformer for Recognition

2021-03-27 · Yaoyao Zhong, Weihong Deng

Recently there has been a growing interest in Transformer not only in NLP but also in computer vision. We wonder if transformer can be used in face recognition and whether it is better than CNNs. Therefore, we investigat…

Face Recognition

ATTN-FIQA: Interpretable Attention-based Face Image Quality Assessment with Vision Transformers

2026-04-21 · Guray Ozgur, Tahar Chettaoui, Eduarda Caldeira, Jan Niklas Kolf 외 arxiv

Face Image Quality Assessment (FIQA) aims to assess the recognition utility of face samples and is essential for reliable face recognition (FR) systems. Existing approaches require computationally expensive procedures su…

Face Image Quality AssessmentFace Recognition