FedPylot: Navigating Federated Learning for Real-Time Object Detection in Internet of Vehicles
Not on the map. Why?
Abstract (arXiv)
The Internet of Vehicles (IoV) emerges as a pivotal component for autonomous driving and intelligent transportation systems (ITS), by enabling low-latency big data processing in a dense interconnected network that comprises vehicles, infrastructures, pedestrians and the cloud. Autonomous vehicles are heavily reliant on machine learning (ML) and can strongly benefit from the wealth of sensory data generated at the edge, which calls for measures to reconcile model training with preserving the privacy of sensitive user data. Federated learning (FL) stands out as a promising solution to train sophisticated ML models in vehicular networks while protecting the privacy of road users and mitigating communication overhead. This paper examines the federated optimization of the cutting-edge YOLOv7 model to tackle real-time object detection amid data heterogeneity, encompassing unbalancedness, concept drift, and label distribution skews. To this end, we introduce FedPylot, a lightweight MPI-based prototype to simulate federated object detection experiments on high-performance computing (HPC) systems, where we safeguard server-client communications using hybrid encryption. Our study factors in accuracy, communication cost, and inference speed, thereby presenting a balanced approach to the challenges faced by autonomous vehicles. We demonstrate promising results for the applicability of FL in IoV and hope that FedPylot will provide a basis for future research into federated real-time object detection. The source code is available at https://github.com/cyprienquemeneur/fedpylot.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 50 of its 91 references that are in the map. First posted on arXiv 5 Jun 2024.
Builds on
50 of 91 references.
References · 50
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
- 2014Microsoft COCO: Common Objects in Contextcited by 17,498
- 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
- 2020End-to-End Object Detection with Transformerscited by 7,384
- 2016Feature Pyramid Networks for Object Detectioncited by 5,021
- 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
- 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
- 2015SSD: Single Shot MultiBox Detectorcited by 3,125
- 2019Advances and Open Problems in Federated Learningcited by 3,021
- 2018Federated Optimization in Heterogeneous Networkscited by 2,971
38 more
- 2018YOLOv3: An Incremental Improvementcited by 2,652
- 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
- 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,624
- 2016YOLO9000: Better, Faster, Strongercited by 1,429
- 2021YOLOX: Exceeding YOLO Series in 2021cited by 1,064
- 2020Adaptive Federated Optimizationcited by 1,036
- 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 978
- 2019Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classificationcited by 836
- 2021Model-Contrastive Federated Learningcited by 762
- 2014Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognitioncited by 719
- 2023DETRs Beat YOLOs on Real-time Object Detectioncited by 526
- 2021Towards Personalized Federated Learningcited by 462
- 2019Distance-IoU Loss: Faster and Better Learning for Bounding Box Regressioncited by 454
- 2020Flower: A Friendly Federated Learning Research Frameworkcited by 449
- 2024YOLOv9: Learning What You Want to Learn Using Programmable Gradient Informationcited by 422
- 2019A Survey of Deep Learning Techniques for Autonomous Drivingcited by 401
- 2020FedML: A Research Library and Benchmark for Federated Machine Learningcited by 298
- 2017Computer Vision for Autonomous Vehicles: Problems, Datasets and State of the Artcited by 182
- 2023A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAScited by 149
- 2021A Survey of Modern Deep Learning based Object Detection Modelscited by 97
- 2021You Only Learn One Representation: Unified Network for Multiple Taskscited by 86
- 2021FedCM: Federated Learning with Client-level Momentumcited by 77
- 2019Accelerating Federated Learning via Momentum Gradient Descentcited by 75
- 2021Federated Learning Meets Blockchain in Edge Computing: Opportunities and Challengescited by 75
- 2022On the Importance and Applicability of Pre-Training for Federated Learningcited by 71
- 2022Where to Begin? On the Impact of Pre-Training and Initialization in Federated Learningcited by 71
- 2023YOLOv6 v3.0: A Full-Scale Reloadingcited by 58
- 2018Complex-YOLO: Real-time 3D Object Detection on Point Cloudscited by 56
- 2022FedDrive: Generalizing Federated Learning to Semantic Segmentation in Autonomous Drivingcited by 41
- 2022Designing Network Design Strategies Through Gradient Path Analysiscited by 32
- 2023AutoFed: Heterogeneity-Aware Federated Multimodal Learning for Robust Autonomous Drivingcited by 32
- 2022Federated Deep Learning Meets Autonomous Vehicle Perception: Design and Verificationcited by 14
- 2022Efficient Federated Learning with Spike Neural Networks for Traffic Sign Recognitioncited by 12
- 2021Making a Case for Federated Learning in the Internet of Vehicles and Intelligent Transportation Systemscited by 10
- 2022Cross-domain Federated Object Detectioncited by 5
- 2023FedDrive v2: an Analysis of the Impact of Label Skewness in Federated Semantic Segmentation for Autonomous Drivingcited by 3
- 2024Federated Learning with Heterogeneous Data Handling for Robust Vehicular Object Detectioncited by 2
- 2023Sparse Federated Training of Object Detection in the Internet of Vehiclescited by 1
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.