Fast-convergent and communication-alleviated heterogeneous hierarchical federated learning in autonomous driving

WB Kou, Q Lin, M Tang, R Ye, S Wang, G Zhu… - arXiv preprint arXiv …, 2024 - arxiv.org
Street Scene Semantic Understanding (denoted as TriSU) is a complex task for autonomous
driving (AD). However, inference model trained from data in a particular geographical region …

Enhancing Large Vision Model in Street Scene Semantic Understanding through Leveraging Posterior Optimization Trajectory

WB Kou, Q Lin, M Tang, S Wang, R Ye, G Zhu… - arXiv preprint arXiv …, 2025 - arxiv.org
To improve the generalization of the autonomous driving (AD) perception model, vehicles
need to update the model over time based on the continuously collected data. As time …