发表机构
Ulsan National Institute of Science and Technology (UNIST)（蔚山科学技术院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对机器人感知深度估计中联邦学习因客户端异构性导致性能下降的问题，本文提出FeDepth框架，通过软聚类建模客户端关系，在多架构上提升了联邦学习的鲁棒性。
AI 中文摘要
尽管近期机器人感知研究强调在不同环境的数据上训练以提升泛化性，但现有多数方法仍依赖集中式学习，其效率低下且难以跨异构机器人平台扩展。联邦学习（FL）提供了一种无需原始数据传输的分布式训练替代方案，但在客户端异构性引发的域偏移下会出现严重性能下降。在实际机器人部署中，不同平台、环境和感知条件的数据分布常存在重叠，难以将客户端划分为完全独立的域，这打破了聚类联邦学习中客户端域完全可分的常见假设。针对机器人感知（尤其是深度估计）中的这一缺口，本文引入两种反映平台、环境和深度分布异构性的现实且未被探索的非独立同分布（non-IID）场景，随后提出FeDepth，一种基于描述符的聚类联邦学习框架，通过软聚类建模客户端关系。与假设簇完全分离的硬聚类方法不同，FeDepth允许客户端参与多个簇，以捕捉机器人环境中常见的连续且模糊的域过渡。大量实验表明，FeDepth在多种深度估计架构上始终优于标准联邦学习和聚类联邦学习基线，为联邦机器人感知提供了实用且有效的解决方案。项目页面可访问this https URL。
英文摘要
Although recent robot perception research emphasizes training on data from diverse environments to improve generalization, most existing methods still rely on centralized learning, which is inefficient and difficult to scale across heterogeneous robot platforms. Federated learning (FL) offers an alternative by enabling distributed training without raw data transfer, but it suffers from severe performance degradation under domain shifts caused by heterogeneity across clients. In real robotic deployments, data distributions often overlap across platforms, environments, and sensing conditions, making it difficult to partition clients into clearly separated domains. However, this characteristic breaks the assumption of clearly separable client domains commonly used in clustered FL. To address this gap in robot perception, particularly in depth estimation, we introduce two realistic and unexplored non-IID scenarios that reflect heterogeneity in terms of platform, environment, and depth distribution. We then propose FeDepth, a descriptor-based clustered FL framework that models client relationships through soft clustering. Unlike hard clustering methods that assume clearly separated clusters, FeDepth allows clients to participate in multiple clusters, capturing continuous and ambiguous domain transitions commonly observed in robotic environments. Extensive experiments demonstrate that FeDepth consistently improves robustness over standard FL and clustered FL baselines across multiple depth estimation architectures, providing a practical and effective solution for federated robot perception. Our project page is available at https://vision3d-lab.github.io/fedepth/.
CommentsAccepted at ECCV 2026. Ganghyeon Lee and Inha Lee contributed equally. Kyungdon Joo is the corresponding author
