FaceLiVTv2: An Improved Hybrid Architecture for Efficient Mobile Face Recognition

• URL: http://arxiv.org/abs/2604.09127v1
• Date: Fri, 10 Apr 2026 09:09:54 GMT
• Title: FaceLiVTv2: An Improved Hybrid Architecture for Efficient Mobile Face Recognition
• Abstract summary: We present an improved version of our FaceLiVT architecture for efficient global--local feature interaction in mobile face recognition.<n>Results show that FaceLiVTv2 consistently improves the accuracy-efficiency trade-off over existing lightweight methods.
• Score: 6.427162946484909
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 recent hybrid CNN-Transformer architectures have advanced global context modeling, striking an effective balance between recognition performance and computational efficiency remains an open challenge. In this work, we present FaceLiVTv2, an improved version of our FaceLiVT hybrid architecture designed for efficient global--local feature interaction in mobile face recognition. At its core is Lite MHLA, a lightweight global token interaction module that replaces the original multi-layer attention design with multi-head linear token projections and affine rescale transformations, reducing redundancy while preserving representational diversity across heads. We further integrate Lite MHLA into a unified RepMix block that coordinates local and global feature interactions and adopts global depthwise convolution for adaptive spatial aggregation in the embedding stage. Under our experimental setup, results on LFW, CA-LFW, CP-LFW, CFP-FP, AgeDB-30, and IJB show that FaceLiVTv2 consistently improves the accuracy-efficiency trade-off over existing lightweight methods. Notably, FaceLiVTv2 reduces mobile inference latency by 22% relative to FaceLiVTv1, achieves speedups of up to 30.8% over GhostFaceNets on mobile devices, and delivers 20-41% latency improvements over EdgeFace and KANFace across platforms while maintaining higher recognition accuracy. These results demonstrate that FaceLiVTv2 offers a practical and deployable solution for real-time face recognition. Code is available at https://github.com/novendrastywn/FaceLiVT.

Related papers

• HoloEv-Net: Efficient Event-based Action Recognition via Holographic Spatial Embedding and Global Spectral Gating [0.571097144710995]
  Event-based Action Recognition (EAR) has attracted significant attention due to high temporal resolution and high dynamic range of event cameras.<n>Existing methods typically suffer from (i) the computational redundancy of dense voxel representations, (ii) structural redundancy inherent in multi-branch architectures, and (iii) the under-utilization of spectral information in capturing global motion patterns.
  arXiv  Detail & Related papers  (2026-02-04T03:42:42Z)
• EVCC: Enhanced Vision Transformer-ConvNeXt-CoAtNet Fusion for Classification [0.5394291557377919]
  Hybrid vision architectures combining Transformers and CNNs have significantly advanced image classification, but they usually do so at significant computational cost.<n>We introduce EVCC, a novel multi-branch architecture integrating the Vision Transformer, lightweight ConvNeXt, and CoAtNet.<n> Experiments across the CIFAR-100, Tobacco3482, CelebA, and Brain Cancer datasets demonstrate EVCC's superiority over powerful models.
  arXiv  Detail & Related papers  (2025-11-24T02:11:19Z)
• High-resolution Photo Enhancement in Real-time: A Laplacian Pyramid Network [73.19214585791268]
  This paper introduces a pyramid network called LLF-LUT++, which integrates global and local operators through closed-form Laplacian pyramid decomposition and reconstruction.<n>Specifically, we utilize an image-adaptive 3D LUT that capitalizes on the global tonal characteristics of downsampled images.<n>LLF-LUT++ not only achieves a 2.64 dB improvement in PSNR on the HDR+ dataset, but also further reduces, with 4K resolution images processed in just 13 ms on a single GPU.
  arXiv  Detail & Related papers  (2025-10-13T16:52:32Z)
• FaceLiVT: Face Recognition using Linear Vision Transformer with Structural Reparameterization For Mobile Device [3.617580194719686]
  FaceLiVT is a lightweight yet powerful face recognition model.<n>It integrates a hybrid Convolution Neural Network (CNN)-Transformer architecture with an innovative and lightweight Multi-Head Linear Attention mechanism.
  arXiv  Detail & Related papers  (2025-06-12T05:36:40Z)
• iFormer: Integrating ConvNet and Transformer for Mobile Application [0.6798775532273751]
  iFormer integrates the fast local representation capacity of convolution with the efficient global modeling ability of self-attention.<n>We conduct comprehensive experiments demonstrating that iFormer outperforms existing lightweight networks across various tasks.
  arXiv  Detail & Related papers  (2025-01-26T02:34:58Z)
• CARE Transformer: Mobile-Friendly Linear Visual Transformer via Decoupled Dual Interaction [77.8576094863446]
  We propose a new detextbfCoupled dutextbfAl-interactive lineatextbfR atttextbfEntion (CARE) mechanism. We first propose an asymmetrical feature decoupling strategy that asymmetrically decouples the learning process for local inductive bias and long-range dependencies. By adopting a decoupled learning way and fully exploiting complementarity across features, our method can achieve both high efficiency and accuracy.
  arXiv  Detail & Related papers  (2024-11-25T07:56:13Z)
• MobileMamba: Lightweight Multi-Receptive Visual Mamba Network [51.33486891724516]
  Previous research on lightweight models has primarily focused on CNNs and Transformer-based designs. We propose the MobileMamba framework, which balances efficiency and performance. MobileMamba achieves up to 83.6% on Top-1, surpassing existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-11-24T18:01:05Z)
• Hyperdimensional Computing Empowered Federated Foundation Model over Wireless Networks for Metaverse [56.384390765357004]
  We propose an integrated federated split learning and hyperdimensional computing framework for emerging foundation models. This novel approach reduces communication costs, computation load, and privacy risks, making it suitable for resource-constrained edge devices in the Metaverse.
  arXiv  Detail & Related papers  (2024-08-26T17:03:14Z)
• Lightweight Vision Transformer with Bidirectional Interaction [59.39874544410419]
  We propose a Fully Adaptive Self-Attention (FASA) mechanism for vision transformer to model the local and global information.<n>Based on FASA, we develop a family of lightweight vision backbones, Fully Adaptive Transformer (FAT) family.
  arXiv  Detail & Related papers  (2023-06-01T06:56:41Z)
• SwiftFormer: Efficient Additive Attention for Transformer-based Real-time Mobile Vision Applications [98.90623605283564]
  We introduce a novel efficient additive attention mechanism that effectively replaces the quadratic matrix multiplication operations with linear element-wise multiplications. We build a series of models called "SwiftFormer" which achieves state-of-the-art performance in terms of both accuracy and mobile inference speed. Our small variant achieves 78.5% top-1 ImageNet-1K accuracy with only 0.8 ms latency on iPhone 14, which is more accurate and 2x faster compared to MobileViT-v2.
  arXiv  Detail & Related papers  (2023-03-27T17:59:58Z)
• Migrating Face Swap to Mobile Devices: A lightweight Framework and A Supervised Training Solution [7.572886749166295]
  MobileFSGAN is a novel lightweight GAN for face swap that can run on mobile devices with much fewer parameters while achieving competitive performance. A lightweight encoder-decoder structure is designed especially for image synthesis tasks, which is only 10.2MB and can run on mobile devices at a real-time speed.
  arXiv  Detail & Related papers  (2022-04-13T05:35:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.