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 faces poor generalization when applied in other regions due to inter-city data domain-shift. Hierarchical Federated Learning (HFL) offers a potential solution for improving TriSU model generalization by collaborative privacy-preserving training over distributed datasets from different cities. Unfortunately, it suffers from slow convergence because data from different cities are with disparate statistical properties. Going beyond existing HFL methods, we propose a Gaussian heterogeneous HFL algorithm (FedGau) to address inter-city data heterogeneity so that convergence can be accelerated. In the proposed FedGau algorithm, both single RGB image and RGB dataset are modelled as Gaussian distributions for aggregation weight design. This approach not only differentiates each RGB image by respective statistical distribution, but also exploits the statistics of dataset from each city in addition to the conventionally considered data volume. With the proposed approach, the convergence is accelerated by 35.5\%-40.6\% compared to existing state-of-the-art (SOTA) HFL methods. On the other hand, to reduce the involved communication resource, we further introduce a novel performance-aware adaptive resource scheduling (AdapRS) policy. Unlike the traditional static resource scheduling policy that exchanges a fixed number of models between two adjacent aggregations, AdapRS adjusts the number of model aggregation at different levels of HFL so that unnecessary communications are minimized. Extensive experiments demonstrate that AdapRS saves 29.65\% communication overhead compared to conventional static resource scheduling policy while maintaining almost the same performance.

翻译：街道场景语义理解（简称TriSU）是自动驾驶（AD）中的一项复杂任务。然而，在特定地理区域数据上训练的推理模型，由于城市间的数据域偏移，在应用于其他区域时面临泛化能力差的问题。层次联邦学习（HFL）通过在不同城市的分布式数据集上进行协作式隐私保护训练，为提升TriSU模型的泛化能力提供了一种潜在解决方案。遗憾的是，由于不同城市的数据具有不同的统计特性，该方法收敛速度缓慢。超越现有的HFL方法，我们提出了一种高斯异构HFL算法（FedGau），以解决城市间的数据异构性问题，从而加速收敛。在所提出的FedGau算法中，单张RGB图像和RGB数据集均被建模为高斯分布，用于设计聚合权重。该方法不仅通过各自的统计分布区分每张RGB图像，还利用了每个城市数据集的统计信息，而不仅仅是传统上考虑的数据量。采用所提出的方法，与现有最先进的HFL方法相比，收敛速度加快了35.5%至40.6%。另一方面，为减少所涉及的通信资源，我们进一步引入了一种新颖的性能感知自适应资源调度（AdapRS）策略。与传统的静态资源调度策略（在两次相邻聚合之间交换固定数量的模型）不同，AdapRS根据HFL不同层次调整模型聚合的数量，从而最小化不必要的通信。大量实验表明，AdapRS在保持几乎相同性能的同时，相比传统静态资源调度策略节省了29.65%的通信开销。