轻量级人脸识别模型，移动端推理速度更快
FaceLiVT: Face Recognition using Linear Vision Transformer with Structural Reparameterization For Mobile Device
- 用线性注意力机制降低计算开销
- 在多个数据集上精度优于现有轻量模型
- 适合资源受限的移动设备实时应用
本文提出FaceLiVT，一种融合卷积神经网络与Transformer结构的轻量级人脸识别模型，采用创新的多头线性注意力（MHLA）机制和重参数化令牌混合器，在降低计算复杂度的同时保持高精度。在LFW、CFP-FP、AgeDB-30、IJB-B和IJB-C等挑战性基准上的评估表明，其性能优于当前最先进的轻量级模型。MHLA显著提升推理速度，使FaceLiVT在移动端实现低延迟高精度识别：相比EdgeFace快8.6倍，比纯ViT模型快21.2倍。该模型在效率与准确率间取得良好平衡，为资源受限平台提供了实用的实时人脸识别方案。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。