Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
144 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Navigating Data Heterogeneity in Federated Learning A Semi-Supervised Federated Object Detection (2310.17097v3)

Published 26 Oct 2023 in cs.CV and cs.DC

Abstract: 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.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (44)
  1. Federated learning based on dynamic regularization. arXiv preprint arXiv:2111.04263, 2021.
  2. Fedseal: Semi-supervised federated learning with self-ensemble learning and negative learning. arXiv preprint arXiv:2110.07829, 2021.
  3. On bridging generic and personalized federated learning for image classification. In International Conference on Learning Representations, 2022.
  4. The cityscapes dataset for semantic urban scene understanding. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 3213–3223, 2016.
  5. Semifl: Semi-supervised federated learning for unlabeled clients with alternate training. Advances in Neural Information Processing Systems, 35:17871–17884, 2022.
  6. Federated learning for vehicular internet of things: Recent advances and open issues. IEEE Open Journal of the Computer Society, 1:45–61, 2020.
  7. Personalized federated learning: A meta-learning approach. arXiv preprint arXiv:2002.07948, 2020.
  8. Cfa: Constraint-based finetuning approach for generalized few-shot object detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 4039–4049, 2022.
  9. Soda10m: a large-scale 2d self/semi-supervised object detection dataset for autonomous driving. arXiv preprint arXiv:2106.11118, 2021.
  10. Federated semi-supervised learning with inter-client consistency & disjoint learning. arXiv preprint arXiv:2006.12097, 2020.
  11. Federated learning without full labels: A survey. arXiv preprint arXiv:2303.14453, 2023.
  12. Towards utilizing unlabeled data in federated learning: A survey and prospective. arXiv preprint arXiv:2002.11545, 2020.
  13. ultralytics/yolov5: v7.0 - YOLOv5 SOTA Realtime Instance Segmentation, November 2022.
  14. Advances and open problems in federated learning. Foundations and Trends® in Machine Learning, 14(1–2):1–210, 2021.
  15. Scaffold: Stochastic controlled averaging for on-device federated learning. arXiv preprint arXiv:1910.06378, 2019.
  16. Revisiting orthogonality regularization: a study for convolutional neural networks in image classification. IEEE Access, 10:69741–69749, 2022.
  17. Supernet training for federated image classification under system heterogeneity, 2022.
  18. Federated semi-supervised learning with prototypical networks. arXiv preprint arXiv:2205.13921, 2022.
  19. Fedcd: Improving performance in non-iid federated learning. arXiv preprint arXiv:2006.09637, 2020.
  20. Federated optimization in heterogeneous networks. arXiv preprint arXiv:1812.06127, 2018.
  21. On the convergence of fedavg on non-iid data. arXiv preprint arXiv:1907.02189, 2019.
  22. Fedbn: Federated learning on non-iid features via local batch normalization. arXiv preprint arXiv:2102.07623, 2021.
  23. Ensemble distillation for robust model fusion in federated learning. arXiv preprint arXiv:2006.07242, 2020.
  24. Focal loss for dense object detection. In Proceedings of the IEEE international conference on computer vision, pages 2980–2988, 2017.
  25. Unbiased teacher for semi-supervised object detection. arXiv preprint arXiv:2102.09480, 2021.
  26. Mml: Maximal multiverse learning for robust fine-tuning of language models. arXiv preprint arXiv:1911.06182, 2019.
  27. Communication-efficient learning of deep networks from decentralized data. In Artificial intelligence and statistics, pages 1273–1282. PMLR, 2017.
  28. Agnostic federated learning. arXiv preprint arXiv:1902.00146, 2019.
  29. Fedltn: Federated learning for sparse and personalized lottery ticket networks. In Computer Vision–ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part XII, pages 69–85. Springer, 2022.
  30. Federated learning for smart healthcare: A survey. ACM Computing Surveys (CSUR), 55(3):1–37, 2022.
  31. State of California Department of Justice. California consumer privacy act. https://oag.ca.gov/privacy/ccpa, 2018.
  32. Orthogonal projection loss. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 12333–12343, 2021.
  33. Adaptive federated optimization. arXiv preprint arXiv:2003.00295, 2020.
  34. Fedpaq: A communication-efficient federated learning method with periodic averaging and quantization. In International Conference on Artificial Intelligence and Statistics, pages 2021–2031. PMLR, 2020.
  35. A simple semi-supervised learning framework for object detection. arXiv preprint arXiv:2005.04757, 2020.
  36. Paul Voigt and Axel Von dem Bussche. The eu general data protection regulation (gdpr). A Practical Guide, 1st Ed., Cham: Springer International Publishing, 10(3152676):10–5555, 2017.
  37. Self-domain adaptation for face anti-spoofing. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pages 2746–2754, 2021.
  38. Efficient teacher: Semi-supervised object detection for yolov5. arXiv preprint arXiv:2302.07577, 2023.
  39. Personalized federated learning with feature alignment and classifier collaboration. In The Eleventh International Conference on Learning Representations, 2023.
  40. End-to-end semi-supervised object detection with soft teacher. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 3060–3069, 2021.
  41. Bdd100k: A diverse driving dataset for heterogeneous multitask learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 2636–2645, 2020.
  42. Improving semi-supervised federated learning by reducing the gradient diversity of models. In 2021 IEEE International Conference on Big Data (Big Data), pages 1214–1225. IEEE, 2021.
  43. When does the student surpass the teacher? federated semi-supervised learning with teacher-student ema. arXiv preprint arXiv:2301.10114, 2023.
  44. Ssda-yolo: Semi-supervised domain adaptive yolo for cross-domain object detection. Computer Vision and Image Understanding, 229:103649, 2023.
Citations (2)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now