mlsanityData to 14 Oct 2026

FedFR: Joint Optimization Federated Framework for Generic and Personalized Face Recognition

arXiv 2112.12496 ↗First posted 23 Dec 2021cs.CV cs.AIcited by 16

Not on the map. Why?

Abstract (arXiv)

Current state-of-the-art deep learning based face recognition (FR) models require a large number of face identities for central training. However, due to the growing privacy awareness, it is prohibited to access the face images on user devices to continually improve face recognition models. Federated Learning (FL) is a technique to address the privacy issue, which can collaboratively optimize the model without sharing the data between clients. In this work, we propose a FL based framework called FedFR to improve the generic face representation in a privacy-aware manner. Besides, the framework jointly optimizes personalized models for the corresponding clients via the proposed Decoupled Feature Customization module. The client-specific personalized model can serve the need of optimized face recognition experience for registered identities at the local device. To the best of our knowledge, we are the first to explore the personalized face recognition in FL setup. The proposed framework is validated to be superior to previous approaches on several generic and personalized face recognition benchmarks with diverse FL scenarios. The source codes and our proposed personalized FR benchmark under FL setup are available at https://github.com/jackie840129/FedFR.

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). Builds on 35 of its 41 references that are in the map. First posted on arXiv 23 Dec 2021.

Builds on

35 of 41 references.

References · 35

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2019Advances and Open Problems in Federated Learningcited by 3,046
  4. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,849
  5. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,475
  6. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,229
  7. 2018Federated Learning with Non-IID Datacited by 1,108
  8. 2018CosFace: Large Margin Cosine Loss for Deep Face Recognitioncited by 971
  9. 2017VGGFace2: A dataset for recognising faces across pose and agecited by 914
  10. 2017A Survey on Multi-Task Learningcited by 840
  11. 2019Towards Federated Learning at Scale: System Designcited by 832
  12. 2021Model-Contrastive Federated Learningcited by 766
23 more
  1. 2017SphereFace: Deep Hypersphere Embedding for Face Recognitioncited by 737
  2. 2020Ensemble Distillation for Robust Model Fusion in Federated Learningcited by 682
  3. 2016MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognitioncited by 624
  4. 2021FedBN: Federated Learning on Non-IID Features via Local Batch Normalizationcited by 571
  5. 2020Circle Loss: A Unified Perspective of Pair Similarity Optimizationcited by 403
  6. 2019A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protectioncited by 374
  7. 2020Think Locally, Act Globally: Federated Learning with Local and Global Representationscited by 325
  8. 2021A Field Guide to Federated Optimizationcited by 315
  9. 2020Personalized Federated Learning: A Meta-Learning Approachcited by 312
  10. 2019Tighter Theory for Local SGD on Identical and Heterogeneous Datacited by 266
  11. 2021WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognitioncited by 223
  12. 2018Federated Meta-Learning with Fast Convergence and Efficient Communicationcited by 155
  13. 2019On the Convergence of Local Descent Methods in Federated Learningcited by 153
  14. 2020Survey of Personalization Techniques for Federated Learningcited by 145
  15. 2020Salvaging Federated Learning by Local Adaptationcited by 142
  16. 2020Federated Learning with Only Positive Labelscited by 55
  17. 2020Performance Optimization for Federated Person Re-identification via Benchmark Analysiscited by 50
  18. 2021SphereFace2: Binary Classification is All You Need for Deep Face Recognitioncited by 42
  19. 2020Vec2Face: Unveil Human Faces from their Blackbox Features in Face Recognitioncited by 36
  20. 2020Unified Representation Learning for Cross Model Compatibilitycited by 30
  21. 2021FedFace: Collaborative Learning of Face Recognition Modelcited by 26
  22. 2021Meta-HAR: Federated Representation Learning for Human Activity Recognitioncited by 21
  23. 2021On Bridging Generic and Personalized Federated Learning for Image Classificationcited by 15

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 4; 2024: 9; 2025: 2.

16 papers.

Sort:

By area:

  1. 2023Efficient Model Personalization in Federated Learning via Client-Specific Prompt Generationcited by 54
  2. 2023ProtoFL: Unsupervised Federated Learning via Prototypical Distillationcited by 12
  3. 2024COALA: A Practical and Vision-Centric Federated Learning Platformcited by 7
  4. 2024Rethinking Personalized Federated Learning with Clustering-based Dynamic Graph Propagationcited by 5
  5. 2022A Survey of Face Recognitioncited by 1
  6. 2023Towards Zero-trust Security for the Metaversecited by 1
  7. 2023Avoid Adversarial Adaption in Federated Learning by Multi-Metric Investigationscited by 1
  8. 2024Trustworthy Personalized Bayesian Federated Learning via Posterior Fine-Tunecited by 1
  9. 2024PAFedFV: Personalized and Asynchronous Federated Learning for Finger Vein Recognitioncited by 1
  10. 2025Uncertainty-Aware Label Refinement on Hypergraphs for Personalized Federated Facial Expression Recognitioncited by 1
  11. 2024Federated Learning Method for Preserving Privacy in Face Recognition Systemcited by 0
  12. 2024Adaptive Hybrid Masking Strategy for Privacy-Preserving Face Recognition Against Model Inversion Attackcited by 0
4 more
  1. 2024AdaFedFR: Federated Face Recognition with Adaptive Inter-Class Representation Learningcited by 0
  2. 2024Federated Learning for Face Recognition via Intra-subject Self-supervised Learningcited by 0
  3. 2024Meta-Learning for Federated Face Recognition in Imbalanced Data Regimescited by 0
  4. 2025Prompt Estimation from Prototypes for Federated Prompt Tuning of Vision Transformerscited by 0