{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T08:37:45Z","timestamp":1775032665512,"version":"3.50.1"},"reference-count":32,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neurorobot."],"abstract":"<jats:p>The rapid advancement of unmanned aerial vehicles (UAVs) in disaster response and environmental monitoring has underscored the growing importance of real-time object detection within UAV swarm networks. However, the non-independent and identically distributed (non-IID) characteristics of data in UAV networks present significant challenges to model convergence and adaptability. To tackle these challenges, this study introduces a robust federated UAV object detection framework tailored for non-IID data distributions. The framework aims to enhance adaptability across clients, thereby improving both detection performance and convergence speed. Our approach includes a self-distillation mechanism that leverages personalized knowledge from local model historical states to guide current local training, striking a balance between specialization and adaptability. Additionally, we propose a drift compensation mechanism to synchronize local and global model updates, mitigating model drift. We conducted extensive experiments on the VisDrone2019-DET dataset, comparing our method to baseline models. Results demonstrate that our approach accelerates convergence speed by approximately 2.2 times and enhances detection performance by around 3%, offering an efficient and robust solution for UAV-based object detection under non-IID conditions.<\/jats:p>","DOI":"10.3389\/fnbot.2026.1649168","type":"journal-article","created":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T05:43:43Z","timestamp":1775022223000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Robust federated learning for UAV object detection: a joint self-distillation and drift compensation approach"],"prefix":"10.3389","volume":"20","author":[{"given":"Yu","family":"Hangsun","sequence":"first","affiliation":[{"name":"School of Communication and Information Engineering, Nanjing University of Posts and Telecommunications","place":["Nanjing, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Changnan","family":"Jiang","sequence":"additional","affiliation":[{"name":"Beihang University","place":["Beijing, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziyuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Toronto","place":["Beijing, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heqing","family":"Ouyang","sequence":"additional","affiliation":[{"name":"The University of Hong Kong","place":["Hong Kong, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengpeng","family":"Chen","sequence":"additional","affiliation":[{"name":"Beihang University","place":["Beijing, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2026,4,1]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1912.00818","article-title":"Federated learning with personalization layers","author":"Arivazhagan","year":"2019","journal-title":"arXiv"},{"key":"B2","volume-title":"Federated Learning Drift Detection: An Empirical Study on the Impact of Concept and Data Drift","author":"Awaysheh","year":"2024"},{"key":"B3","doi-asserted-by":"publisher","first-page":"908814","DOI":"10.3389\/fpls.2022.908814","article-title":"An EMD-based adaptive client selection algorithm for federated learning in heterogeneous data scenarios","volume":"13","author":"Chen","year":"2022","journal-title":"Front Plant Sci"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2501.11167","article-title":"A new scheme to enhance convergence rate and robustness in federated learning","year":"2025","journal-title":"arXiv"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2210.10970","article-title":"Federated learning via unmanned aerial vehicle","author":"Fu","year":"2022","journal-title":"arXiv"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1109\/CAMAD59638.2023.10478423","article-title":"Blockchain-enabled Clustered and Scalable Federated Learning (BCS-FL) framework in UAV networks","author":"Hafeez","year":"2024","journal-title":"arXiv"},{"key":"B7","article-title":"\u201cFeature norm regularized federated learning: utilizing data disparities for model performance gains,\u201d","volume-title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence (IJCAI-24)","author":"Hu","year":"2024"},{"key":"B8","article-title":"\u201cOSR: toward developing efficient federated learning-based human activity recognition using optimal server representations,\u201d","author":"Khazaei","year":"2025","journal-title":"ICASSP 2025"},{"key":"B9","article-title":"\u201cFederated optimization in heterogeneous networks,\u201d","volume-title":"Proceedings of Machine Learning and Systems (MLSys)","author":"Li","year":"2020"},{"key":"B10","doi-asserted-by":"publisher","first-page":"244","DOI":"10.1109\/MNET.011.2000842","article-title":"Federated learning for 6G communications: challenges, methods, and future directions","volume":"35","author":"Liu","year":"2021","journal-title":"IEEE Netw"},{"key":"B11","doi-asserted-by":"crossref","DOI":"10.1109\/ASIANCON62057.2024.10838085","article-title":"\u201cSecuring data privacy in machine learning: the FedAvg of federated learning approach,\u201d","volume-title":"Proceedings of the 2024 4th Asian Conference on Innovation in Technology (ASIANCON)","author":"Mehta","year":"2024"},{"key":"B12","doi-asserted-by":"publisher","first-page":"1622","DOI":"10.1109\/COMST.2021.3075439","article-title":"Federated learning for Internet of Things: a comprehensive survey","volume":"23","author":"Nguyen","year":"2021","journal-title":"IEEE Commun. Surv. Tutorials"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-31891-7_2","article-title":"Decentralized federated learning methods for reducing communication cost and energy consumption in UAV networks","author":"Pan","year":"2023","journal-title":"arXiv"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1145\/3243394.3243692","article-title":"Efficient ConvNet-based object detection for unmanned aerial vehicles by selective tile processing","author":"Plastiras","year":"2019","journal-title":"arXiv"},{"key":"B15","first-page":"19872","article-title":"\u201cFederated learning on non-IID data silos: a benchmark study,\u201d","volume-title":"Advances in Neural Information Processing Systems (NeurIPS) 35","author":"Qu","year":"2022"},{"key":"B16","doi-asserted-by":"publisher","first-page":"23844","DOI":"10.1038\/s41598-024-74577-0","article-title":"The potential of federated learning for self-configuring medical object detection in heterogeneous data distributions","volume":"14","author":"Rashidi","year":"2024","journal-title":"Scient. Rep"},{"key":"B17","doi-asserted-by":"publisher","first-page":"149","DOI":"10.3390\/rs16010149","article-title":"A survey of object detection for UAVs based on deep learning","volume":"16","author":"Tang","year":"2023","journal-title":"Remote Sens"},{"key":"B18","doi-asserted-by":"publisher","first-page":"2150","DOI":"10.3390\/math12142150","article-title":"An effective federated object detection framework with dynamic differential privacy","volume":"12","author":"Wang","year":"2024","journal-title":"Mathematics"},{"key":"B19","first-page":"7611","article-title":"\u201cTackling the objective inconsistency problem in heterogeneous federated optimization,\u201d","volume-title":"Advances in Neural Information Processing Systems","author":"Wang","year":"2020"},{"key":"B20","doi-asserted-by":"publisher","first-page":"261","DOI":"10.3390\/drones8060261","article-title":"EUAVDet: an efficient and lightweight object detector for UAV aerial images with an edge-based computing platform","volume":"8","author":"Wu","year":"2024","journal-title":"Drones"},{"key":"B21","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1109\/MGRS.2021.3115137","article-title":"Deep learning for UAV based object detection and tracking: a survey","volume":"10","author":"Wu","year":"2021","journal-title":"IEEE Geosci. Remote Sens. Magaz"},{"key":"B22","doi-asserted-by":"publisher","first-page":"2281","DOI":"10.1109\/ACCESS.2017.2764419","article-title":"Vision-based real-time aerial object localization and tracking for UAV sensing system","volume":"5","author":"Wu","year":"2017","journal-title":"IEEE Access"},{"key":"B23","doi-asserted-by":"publisher","first-page":"3767","DOI":"10.1109\/TII.2023.3342897","article-title":"Differentially private federated learning for multitask objective recognition","volume":"20","author":"Xie","year":"2024","journal-title":"IEEE Trans. Indust. Informat"},{"key":"B24","article-title":"\u201cAsynchronous federated learning for real-time multiple licence plate recognition through semantic communication,\u201d","author":"Xie","year":"2023","journal-title":"ICASSP 2023"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2107.00233","article-title":"FedMix: approximation of mixup under mean augmented federated learning","author":"Yoon","year":"2021","journal-title":"arXiv"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2212.14360","article-title":"Characterization of the global bias problem in aerial federated learning","author":"Zhagypar","year":"2022","journal-title":"arXiv"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2307.04905","article-title":"FedYolo: augmenting federated learning with pretrained transformers","author":"Zhang","year":"2023","journal-title":"arXiv"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2201.01230","article-title":"Robust semi-supervised federated learning for images automatic recognition in internet of drones","author":"Zhang","year":"2022","journal-title":"arXiv"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1145\/3570361.3592517","article-title":"AutoFed: heterogeneity-aware federated multimodal learning for robust autonomous driving","author":"Zheng","year":"2023","journal-title":"arXiv"},{"key":"B30","first-page":"2661","article-title":"\u201cVision meets drones: a challenge,\u201d","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW)","author":"Zhu","year":"2019"},{"key":"B31","first-page":"2778","article-title":"\u201cTPH-YOLOv5: improved YOLOv5 based on transformer prediction head for object detection on drone-captured scenarios,\u201d","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) Workshops","author":"Zhu","year":""},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2108.11539","article-title":"TPH-YOLOv5: improved YOLOv5 based on transformer prediction head for object detection on drone-captured scenarios","author":"Zhu","year":"","journal-title":"arXiv"}],"container-title":["Frontiers in Neurorobotics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2026.1649168\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T05:43:47Z","timestamp":1775022227000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2026.1649168\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,1]]},"references-count":32,"alternative-id":["10.3389\/fnbot.2026.1649168"],"URL":"https:\/\/doi.org\/10.3389\/fnbot.2026.1649168","relation":{},"ISSN":["1662-5218"],"issn-type":[{"value":"1662-5218","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,1]]},"article-number":"1649168"}}