Federated Unsupervised Semantic Segmentation

2025-05-29 · Evangelos Charalampakis, Vasileios Mygdalis, Ioannis Pitas

This work explores the application of Federated Learning (FL) in 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 support reproducibility, full code will be released upon manuscript acceptance.

📄 PDF Abstract BibTeX arXiv:2505.23292

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning Image Segmentation Segmentation Semantic Segmentation Unsupervised Semantic Segmentation

When Cars meet Drones: Hyperbolic Federated Learning for Source-Free Domain Adaptation in Adverse Weather

2024-03-20 · Giulia Rizzoli, Matteo Caligiuri, Donald Shenaj, Francesco Barbato 외

In Federated Learning (FL), multiple clients collaboratively train a global model without sharing private data. In semantic segmentation, the Federated source Free Domain Adaptation (FFreeDA) setting is of particular int…

Autonomous Vehicles Domain Adaptation Federated Learning Segmentation+2

FedSeg: Class-Heterogeneous Federated Learning for Semantic Segmentation

2023-01-01 · CVPR 2023 1 · Jiaxu Miao, Zongxin Yang, Leilei Fan, Yi Yang

Federated Learning (FL) is a distributed learning paradigm that collaboratively learns a global model across multiple clients with data privacy-preserving. Although many FL algorithms have been proposed for classific…

Contrastive Learning Federated Learning Privacy Preserving Segmentation+1

FedS2R: One-Shot Federated Domain Generalization for Synthetic-to-Real Semantic Segmentation in Autonomous Driving

2025-07-26 · Tao Lian, Jose L. Gómez, Antonio M. López arxiv

Federated domain generalization has shown promising progress in image classification by enabling collaborative training across multiple clients without sharing raw data. However, its potential in the semantic segmentatio…

Knowledge Distillation Domain Generalization Semantic Segmentation Image Classification

FedDrive v2: an Analysis of the Impact of Label Skewness in Federated Semantic Segmentation for Autonomous Driving

2023-09-23 · Eros Fanì, Marco Ciccone, Barbara Caputo

We propose FedDrive v2, an extension of the Federated Learning benchmark for Semantic Segmentation in Autonomous Driving. While the first version aims at studying the effect of domain shift of the visual features across …

Autonomous Driving Domain Generalization Federated Learning Segmentation+2

Unsupervised Universal Image Segmentation

2023-12-28 · CVPR 2024 1 · Dantong Niu, Xudong Wang, Xinyang Han, Long Lian 외

Several unsupervised image segmentation approaches have been proposed which eliminate the need for dense manually-annotated segmentation masks; current models separately handle either semantic segmentation (e.g., STEGO) …

Image Segmentation Instance Segmentation Panoptic Segmentation Segmentation+8