FedDrive：将联邦学习推广到自动驾驶中的语义分割
FedDrive: Generalizing Federated Learning to Semantic Segmentation in Autonomous Driving
AI总结：
本文提出FedDrive基准，针对自动驾驶语义分割中的联邦学习，结合统计异质性与领域泛化挑战，通过深入分析现有算法并引入风格迁移方法，证明正确处理归一化统计量和风格迁移能有效提升模型泛化性能。
摘要：
语义分割对于使自动驾驶车辆实现自主至关重要，它通过将单个像素分配给已知类别来帮助车辆理解周围环境。然而，语义分割处理的是从用户车辆收集的敏感数据，因此保护客户端隐私成为首要关注的问题。出于类似原因，联邦学习最近被提出作为一种新的机器学习范式，旨在学习一个全局模型，同时保护隐私并利用数百万远程设备上的数据。尽管在该主题上已有若干努力，但迄今为止还没有工作明确解决自动驾驶语义分割中联邦学习所面临的挑战。为了填补这一空白，我们提出了FedDrive，这是一个新的基准，包含三种设置和两个数据集，纳入了统计异质性和领域泛化的现实世界挑战。我们通过深入分析对联邦学习文献中的最先进算法进行了基准测试，并将它们与风格迁移方法相结合以提高其泛化能力。我们证明，正确处理归一化统计量对于应对上述挑战至关重要。此外，风格迁移在处理显著外观变化时能够提升性能。官方网站：https://feddrive.github.io。
英文摘要：
Semantic Segmentation is essential to make self-driving vehicles autonomous, enabling them to understand their surroundings by assigning individual pixels to known categories. However, it operates on sensible data collected from the users' cars; thus, protecting the clients' privacy becomes a primary concern. For similar reasons, Federated Learning has been recently introduced as a new machine learning paradigm aiming to learn a global model while preserving privacy and leveraging data on millions of remote devices. Despite several efforts on this topic, no work has explicitly addressed the challenges of federated learning in semantic segmentation for driving so far. To fill this gap, we propose FedDrive, a new benchmark consisting of three settings and two datasets, incorporating the real-world challenges of statistical heterogeneity and domain generalization. We benchmark state-of-the-art algorithms from the federated learning literature through an in-depth analysis, combining them with style transfer methods to improve their generalization ability. We demonstrate that correctly handling normalization statistics is crucial to deal with the aforementioned challenges. Furthermore, style transfer improves performance when dealing with significant appearance shifts. Official website: https://feddrive.github.io.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
