mlsanityData to 7 Oct 2026

EdgeFace: Efficient Face Recognition Model for Edge Devices

arXiv 2307.01838 ↗First posted 4 Jul 2023cs.CV cs.CRcited by 33

Not on the map. Why?

Abstract (arXiv)

In this paper, we present EdgeFace, a lightweight and efficient face recognition network inspired by the hybrid architecture of EdgeNeXt. By effectively combining the strengths of both CNN and Transformer models, and a low rank linear layer, EdgeFace achieves excellent face recognition performance optimized for edge devices. The proposed EdgeFace network not only maintains low computational costs and compact storage, but also achieves high face recognition accuracy, making it suitable for deployment on edge devices. Extensive experiments on challenging benchmark face datasets demonstrate the effectiveness and efficiency of EdgeFace in comparison to state-of-the-art lightweight models and deep face recognition models. Our EdgeFace model with 1.77M parameters achieves state of the art results on LFW (99.73%), IJB-B (92.67%), and IJB-C (94.85%), outperforming other efficient models with larger computational complexities. The code to replicate the experiments will be made available publicly.

Key facts. Cited by 33 papers in the map (data through 7 Oct 2026). Builds on 39 of its 67 references that are in the map. First posted on arXiv 4 Jul 2023.

Builds on

39 of 67 references.

References · 39

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  5. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  6. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  7. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  8. 2022A ConvNet for the 2020scited by 3,545
  9. 2017ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devicescited by 1,194
  10. 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,132
  11. 2016SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizecited by 1,054
  12. 2021Transformers in Vision: A Surveycited by 1,009
27 more
  1. 2018CosFace: Large Margin Cosine Loss for Deep Face Recognitioncited by 968
  2. 2020Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuningcited by 658
  3. 2021MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformercited by 636
  4. 2014Learning Face Representation from Scratchcited by 451
  5. 2019GhostNet: More Features from Cheap Operationscited by 410
  6. 2022AdaFace: Quality Adaptive Margin for Face Recognitioncited by 390
  7. 2021XCiT: Cross-Covariance Image Transformerscited by 335
  8. 2021MagFace: A Universal Representation for Face Recognition and Quality Assessmentcited by 332
  9. 2020CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognitioncited by 320
  10. 2017Cross-Age LFW: A Database for Studying Cross-Age Face Recognition in Unconstrained Environmentscited by 258
  11. 2021Mobile-Former: Bridging MobileNet and Transformercited by 234
  12. 2021WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognitioncited by 221
  13. 2018MobileFaceNets: Efficient CNNs for Accurate Real-Time Face Verification on Mobile Devicescited by 180
  14. 2021ElasticFace: Elastic Margin Loss for Deep Face Recognitioncited by 143
  15. 2015A Light CNN for Deep Face Representation with Noisy Labelscited by 126
  16. 2022EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applicationscited by 121
  17. 2019MixConv: Mixed Depthwise Convolutional Kernelscited by 108
  18. 2017Shift: A Zero FLOP, Zero Parameter Alternative to Spatial Convolutionscited by 93
  19. 2022Killing Two Birds with One Stone:Efficient and Robust Training of Face Recognition CNNs by Partial FCcited by 73
  20. 2020Model Rubik's Cube: Twisting Resolution, Depth and Width for TinyNetscited by 49
  21. 2021MixFaceNets: Extremely Efficient Face Recognition Networkscited by 36
  22. 2021PocketNet: Extreme Lightweight Face Recognition Network using Neural Architecture Search and Multi-Step Knowledge Distillationcited by 36
  23. 2019VarGFaceNet: An Efficient Variable Group Convolutional Neural Network for Lightweight Face Recognitioncited by 30
  24. 2021QMagFace: Simple and Accurate Quality-Aware Face Recognitioncited by 25
  25. 2022QuantFace: Towards Lightweight Face Recognition by Synthetic Data Low-bit Quantizationcited by 18
  26. 2018MobiFace: A Lightweight Deep Learning Face Recognition on Mobile Devicescited by 12
  27. 2019VarGNet: Variable Group Convolutional Neural Network for Efficient Embedded Computingcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 3; 2025: 9; 2026: 18.

33 papers.

Sort:

By area:

  1. 2024SDFR: Synthetic Data for Face Recognition Competitioncited by 28
  2. 2023SynthDistill: Face Recognition with Knowledge Distillation from Synthetic Datacited by 9
  3. 2023EFaR 2023: Efficient Face Recognition Competitioncited by 7
  4. 2025xEdgeFace: Efficient Cross-Spectral Face Recognition for Edge Devicescited by 5
  5. 2025Benchmarking Multimodal Large Language Models for Face Recognitioncited by 5
  6. 2024Unveiling Synthetic Faces: How Synthetic Datasets Can Expose Real Identitiescited by 3
  7. 2025FaceLiVT: Face Recognition using Linear Vision Transformer with Structural Reparameterization For Mobile Devicecited by 3
  8. 2026Evaluating Multimodal Large Language Models for Heterogeneous Face Recognitioncited by 3
  9. 2026FaceLiVTv2: An Improved Hybrid Architecture for Efficient Mobile Face Recognitioncited by 3
  10. 2025Investigation of Accuracy and Bias in Face Recognition Trained with Synthetic Datacited by 2
  11. 2025Securing Face and Fingerprint Templates in Humanitarian Biometric Systemscited by 2
  12. 2023Efficient Verification-Based Face Identificationcited by 1
21 more
  1. 2024SymFace: Additional Facial Symmetry Loss for Deep Face Recognitioncited by 1
  2. 2025Leveraging Simultaneous Usage of Edge GPU Hardware Engines for Video Face Detection and Recognitioncited by 1
  3. 2025EdgeDoc: Hybrid CNN-Transformer Model for Accurate Forgery Detection and Localization in ID Documentscited by 1
  4. 2026IDSelect: A RL-Based Cost-Aware Selection Agent for Video-based Multi-Modal Person Recognitioncited by 1
  5. 2026A Deeper Dive into the Irreversibility of PolyProtect: Making Protected Face Templates Harder to Invertcited by 1
  6. 2026Lightweight Cross-Spectral Face Recognition via Contrastive Alignment and Distillationcited by 1
  7. 2025Enhancing Domain Diversity in Synthetic Data Face Recognition with Dataset Fusioncited by 0
  8. 2025Identity-Preserving Aging and De-Aging of Faces in the StyleGAN Latent Spacecited by 0
  9. 2026Real-Time Multi-Modal Embedded Vision Framework for Object Detection Facial Emotion Recognition and Biometric Identification on Low-Power Edge Platformscited by 0
  10. 2026Adversarial Camouflagecited by 0
  11. 2026DriveFace: A Cross-Spectral Through-Glass Face Dataset for On-the-Move Vehicular Border Controlcited by 0
  12. 2026Benchmarking Face Recognition without Real Facescited by 0
  13. 2026Quality-Aware Multimodal Fusion Reveals Implicit Identity in Valence-Arousal Featurescited by 0
  14. 2026GaitFace: A Multimodal Dataset for Long-Range Person Identificationcited by 0
  15. 2026On the Use of Synthetic Data for Threshold Calibration in Face Recognition: Performance and Security Implications for Border Control Systemscited by 0
  16. 2026Improving Low-Resolution Face Recognition under Limited Data: How Synthetic Data Generation Can Close the Domain Gapcited by 0
  17. 2026ClassVision: AI-Powered Classroom Attendance Systemcited by 0
  18. 2026SynThermFace: Amplifying Limited Paired Data for Visible-Thermal Face Recognition via Synthetic Data Generationcited by 0
  19. 2026Towards Robust Classroom Attendance: A Comprehensive Evaluation of Face Detection and Recognition Modelscited by 0
  20. 2026MIRAGE: Full-Body Bystander Privacy for Smart Glasses with Consent-Based Restorationcited by 0
  21. 2026Is it Possible to Generate Irreversible PolyProtected Templates from Face Embeddings using System-Specific Keys?cited by 0