mlsanityData to 7 Oct 2026

Navigating Data Heterogeneity in Federated Learning A Semi-Supervised Federated Object Detection

arXiv 2310.17097 ↗First posted 26 Oct 2023cs.CV cs.DCcited by 4

Not on the map. Why?

Abstract (arXiv)

Federated Learning (FL) has emerged as a potent framework for training models across distributed data sources while maintaining data privacy. Nevertheless, it faces challenges with limited high-quality labels and non-IID client data, particularly in applications like autonomous driving. To address these hurdles, we navigate the uncharted waters of Semi-Supervised Federated Object Detection (SSFOD). We present a pioneering SSFOD framework, designed for scenarios where labeled data reside only at the server while clients possess unlabeled data. Notably, our method represents the inaugural implementation of SSFOD for clients with 0% labeled non-IID data, a stark contrast to previous studies that maintain some subset of labels at each client. We propose FedSTO, a two-stage strategy encompassing Selective Training followed by Orthogonally enhanced full-parameter training, to effectively address data shift (e.g. weather conditions) between server and clients. Our contributions include selectively refining the backbone of the detector to avert overfitting, orthogonality regularization to boost representation divergence, and local EMA-driven pseudo label assignment to yield high-quality pseudo labels. Extensive validation on prominent autonomous driving datasets (BDD100K, Cityscapes, and SODA10M) attests to the efficacy of our approach, demonstrating state-of-the-art results. Remarkably, FedSTO, using just 20-30% of labels, performs nearly as well as fully-supervised centralized training methods.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 35 of its 43 references that are in the map. First posted on arXiv 26 Oct 2023.

Builds on

35 of 43 references.

References · 35

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  3. 2019Advances and Open Problems in Federated Learningcited by 3,021
  4. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  5. 2018BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learningcited by 1,282
  6. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,220
  7. 2020Adaptive Federated Optimizationcited by 1,036
  8. 2020Ensemble Distillation for Robust Model Fusion in Federated Learningcited by 678
  9. 2021FedBN: Federated Learning on Non-IID Features via Local Batch Normalizationcited by 565
  10. 2021Federated Learning Based on Dynamic Regularizationcited by 555
  11. 2019Agnostic Federated Learningcited by 451
  12. 2019FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantizationcited by 349
23 more
  1. 2021End-to-End Semi-Supervised Object Detection with Soft Teachercited by 315
  2. 2020Personalized Federated Learning: A Meta-Learning Approachcited by 309
  3. 2021Unbiased Teacher for Semi-Supervised Object Detectioncited by 305
  4. 2020A Simple Semi-Supervised Learning Framework for Object Detectioncited by 282
  5. 2021Federated Learning for Smart Healthcare: A Surveycited by 182
  6. 2019SCAFFOLD: Stochastic Controlled Averaging for Federated Learningcited by 174
  7. 2020Federated Semi-Supervised Learning with Inter-Client Consistency & Disjoint Learningcited by 112
  8. 2023Personalized Federated Learning with Feature Alignment and Classifier Collaborationcited by 97
  9. 2021Self-Domain Adaptation for Face Anti-Spoofingcited by 49
  10. 2021SemiFL: Semi-Supervised Federated Learning for Unlabeled Clients with Alternate Trainingcited by 45
  11. 2021Orthogonal Projection Losscited by 44
  12. 2021SODA10M: A Large-Scale 2D Self/Semi-Supervised Object Detection Dataset for Autonomous Drivingcited by 43
  13. 2020Towards Utilizing Unlabeled Data in Federated Learning: A Survey and Prospectivecited by 27
  14. 2022SSDA-YOLO: Semi-supervised Domain Adaptive YOLO for Cross-Domain Object Detectioncited by 19
  15. 2023Efficient Teacher: Semi-Supervised Object Detection for YOLOv5cited by 17
  16. 2020FedCD: Improving Performance in non-IID Federated Learningcited by 13
  17. 2023Federated Learning without Full Labels: A Surveycited by 12
  18. 2022Federated Semi-Supervised Learning with Prototypical Networkscited by 8
  19. 2022CFA: Constraint-based Finetuning Approach for Generalized Few-Shot Object Detectioncited by 5
  20. 2021FedSEAL: Semi-Supervised Federated Learning with Self-Ensemble Learning and Negative Learningcited by 4
  21. 2022Supernet Training for Federated Image Classification under System Heterogeneitycited by 4
  22. 2023When does the student surpass the teacher? Federated Semi-supervised Learning with Teacher-Student EMAcited by 4
  23. 2019MML: Maximal Multiverse Learning for Robust Fine-Tuning of Language Modelscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 2.

4 papers.

  1. 2024Handling Spatial-Temporal Data Heterogeneity for Federated Continual Learning via Tail Anchorcited by 8
  2. 2025SAFE: Self-Adjustment Federated Learning Framework for Remote Sensing Collaborative Perceptioncited by 1
  3. 2026ProxyFL: A Proxy-Guided Framework for Federated Semi-Supervised Learningcited by 0
  4. 2026Federated Learning of Spiking Neural Networks under Heterogeneous Temporal Resolutionscited by 0