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

TL;DR

FedS2R introduces a novel one-shot federated domain generalization framework for synthetic-to-real semantic segmentation in autonomous driving, effectively leveraging multi-client knowledge distillation and data augmentation.

Contribution

It is the first to propose a one-shot federated domain generalization method specifically for synthetic-to-real semantic segmentation in autonomous driving.

Findings

Global model outperforms individual client models.

Achieves near-centralized performance with only 2 mIoU points difference.

Effective in real-world autonomous driving datasets.

Abstract

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 segmentation of autonomous driving remains underexplored. In this paper, we propose FedS2R, the first one-shot federated domain generalization framework for synthetic-to-real semantic segmentation in autonomous driving. FedS2R comprises two components: an inconsistency-driven data augmentation strategy that generates images for unstable classes, and a multi-client knowledge distillation scheme with feature fusion that distills a global model from multiple client models. Experiments on five real-world datasets, Cityscapes, BDD100K, Mapillary, IDD, and ACDC, show that the global model significantly outperforms individual client models and is only 2 mIoU points behind the model trained with simultaneous access to all client data. These results demonstrate the effectiveness of FedS2R in synthetic-to-real semantic segmentation for autonomous driving under federated learning