FedDrive v2: an Analysis of the Impact of Label Skewness in Federated Semantic Segmentation for Autonomous Driving
Preprint
Abstract
We propose FedDrive v2, an extension of the Federated Learning benchmark for Semantic Segmentation in Autonomous Driving. While the first version aims at studying the effect of domain shift of the visual features across clients, in this work, we focus on the distribution skewness of the labels. We propose six new federated scenarios to investigate how label skewness affects the performance of segmentation models and compare it with the effect of domain shift. Finally, we study the impact of using the domain information during testing. Official website: https://feddrive.github.ioKeywords
All Related Versions
This publication has 10 references indexed in Scilit:
- Federated Vehicular Transformers and Their Federations: Privacy-Preserving Computing and Cooperation for Autonomous DrivingIEEE Transactions on Intelligent Vehicles, 2022
- BiSeNet V2: Bilateral Network with Guided Aggregation for Real-Time Semantic SegmentationInternational Journal of Computer Vision, 2021
- Privacy-Preserved Federated Learning for Autonomous DrivingIEEE Transactions on Intelligent Transportation Systems, 2021
- FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Space2021
- Multi-Source Domain Adaptation with Collaborative Learning for Semantic Segmentation2021
- Siloed Federated Learning for Multi-centric Histopathology Datasets2020
- IDDA: A Large-Scale Multi-Domain Dataset for Autonomous DrivingIEEE Robotics and Automation Letters, 2020
- Federated Learning for Vehicular Internet of Things: Recent Advances and Open IssuesIEEE Open Journal of the Computer Society, 2020
- A review of semantic segmentation using deep neural networksInternational Journal of Multimedia Information Retrieval, 2017
- The Cityscapes Dataset for Semantic Urban Scene Understanding2016