This work explores the application of Federated Learning (FL) to Unsupervised Semantic image Segmentation (USS). Recent USS methods extract pixel-level features using frozen visual foundation models and refine them through self-supervised objectives that encourage semantic grouping. These features are then grouped to semantic clusters to produce segmentation masks. Extending these ideas to federated settings requires feature representation and cluster centroid alignment across distributed clients, an inherently difficult task under heterogeneous data distributions in the absence of supervision. To address this, we propose FUSS (Federated Unsupervised image Semantic Segmentation) which is, to our knowledge, the first framework to enable fully decentralized, label-free semantic segmentation training. FUSS introduces novel federation strategies that promote global consistency in feature and prototype space, jointly optimizing local segmentation heads and shared semantic centroids. Experiments on both benchmark and real-world datasets, including binary and multi-class segmentation tasks, show that FUSS consistently outperforms local-only client trainings as well as extensions of classical FL algorithms under varying client data distributions. To fully support reproducibility, the source code, data partitioning scripts, and implementation details are publicly available at: https://github.com/evanchar/FUSS

翻译：本研究探索了联邦学习（FL）在无监督语义图像分割（USS）中的应用。现有USS方法利用冻结的视觉基础模型提取像素级特征，并通过鼓励语义分组的自监督目标进行优化，随后将这些特征聚类至语义簇以生成分割掩码。将这些思想扩展至联邦环境需要在分布式客户端间实现特征表示与聚类质心对齐，这在无监督的异构数据分布下本质上是困难的任务。为此，我们提出了FUSS（联邦无监督图像语义分割）框架——据我们所知，这是首个实现完全去中心化、无标签语义分割训练的框架。FUSS引入了新颖的联邦策略，以促进特征空间与原型空间的全局一致性，并联合优化本地分割头与共享语义质心。在基准数据集和真实数据集（包括二分类与多类分割任务）上的实验表明，在不同客户端数据分布下，FUSS始终优于纯本地客户端训练以及经典FL算法的扩展方案。为全面支持可复现性，源代码、数据划分脚本及实现细节已公开于：https://github.com/evanchar/FUSS