Federated Learning (FL) has emerged as a potent framework for training models across distributed data sources while maintaining data privacy. Nevertheless, it faces challenges with limited high-quality labels and non-IID client data, particularly in applications like autonomous driving. To address these hurdles, we navigate the uncharted waters of Semi-Supervised Federated Object Detection (SSFOD). We present a pioneering SSFOD framework, designed for scenarios where labeled data reside only at the server while clients possess unlabeled data. Notably, our method represents the inaugural implementation of SSFOD for clients with 0% labeled non-IID data, a stark contrast to previous studies that maintain some subset of labels at each client. We propose FedSTO, a two-stage strategy encompassing Selective Training followed by Orthogonally enhanced full-parameter training, to effectively address data shift (e.g. weather conditions) between server and clients. Our contributions include selectively refining the backbone of the detector to avert overfitting, orthogonality regularization to boost representation divergence, and local EMA-driven pseudo label assignment to yield high-quality pseudo labels. Extensive validation on prominent autonomous driving datasets (BDD100K, Cityscapes, and SODA10M) attests to the efficacy of our approach, demonstrating state-of-the-art results. Remarkably, FedSTO, using just 20-30% of labels, performs nearly as well as fully-supervised centralized training methods.

翻译：联邦学习（FL）已成为一种在分布式数据源上训练模型同时维护数据隐私的强大框架。然而，它在高质量标签有限及客户端数据非独立同分布（non-IID）的场景下面临挑战，尤其是在自动驾驶等应用中。为解决这些难题，我们探索了半监督联邦目标检测（SSFOD）这一未充分研究的领域。我们提出了一种开创性的SSFOD框架，专为标签数据仅存在于服务器端而客户端拥有无标签数据的场景设计。值得注意的是，我们的方法首次实现了客户端完全无标签（0%标签率且数据非IID）情况下的SSFOD，这与先前研究中每个客户端保留部分标签的做法形成鲜明对比。我们提出FedSTO，一种包含选择性训练与正交增强全参数训练的两阶段策略，以有效应对服务器与客户端之间的数据偏移（如天气条件）。我们的贡献包括：选择性优化检测器骨干网络以防止过拟合；引入正交正则化增强表示多样性；以及通过局部指数移动平均（EMA）驱动的伪标签分配生成高质量伪标签。在主流自动驾驶数据集（BDD100K、Cityscapes和SODA10M）上的大量实验验证了该方法的高效性，展示了最先进的结果。值得注意的是，FedSTO仅使用20-30%的标签即可达到与全监督集中式训练方法几乎相同的性能。