首个无需标签的联邦语义分割框架，实现跨设备无监督协同分割
Federated Unsupervised Semantic Segmentation
- 采用联邦学习框架，通过共享特征与聚类中心提升分布式模型一致性
- 在多类和二分类任务中均优于本地训练及传统联邦算法
- 适用于隐私敏感场景的跨设备图像分割，如医疗影像分析
本文探索将联邦学习（FL）应用于无监督语义图像分割（USS）。近期的USS方法利用冻结的视觉基础模型提取像素级特征，并通过自监督目标优化特征以促进语义分组，再聚类生成分割掩码。将此类方法扩展至联邦设置面临挑战：在缺乏标注且数据分布异构的情况下，需对齐各客户端的特征表示与聚类中心。为此，我们提出FUSS（Federated Unsupervised Semantic Segmentation），据我们所知，这是首个支持完全去中心化、无标签语义分割训练的框架。FUSS引入新型联邦策略，在特征空间与原型空间共同促进全局一致性，联合优化本地分割头与共享语义中心。在基准与真实世界数据集上的实验表明，无论客户端数据分布如何变化，FUSS始终优于本地训练及经典联邦算法的扩展。为保障可复现性，源代码、数据划分脚本与实现细节已公开于：https://github.com/evanchar/FUSS
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。