|国家预印本平台
首页|FedEMA: Federated Exponential Moving Averaging with Negative Entropy Regularizer in Autonomous Driving

FedEMA: Federated Exponential Moving Averaging with Negative Entropy Regularizer in Autonomous Driving

FedEMA: Federated Exponential Moving Averaging with Negative Entropy Regularizer in Autonomous Driving

来源:Arxiv_logoArxiv
英文摘要

Street Scene Semantic Understanding (denoted as S3U) is a crucial but complex task for autonomous driving (AD) vehicles. Their inference models typically face poor generalization due to domain-shift. Federated Learning (FL) has emerged as a promising paradigm for enhancing the generalization of AD models through privacy-preserving distributed learning. However, these FL AD models face significant temporal catastrophic forgetting when deployed in dynamically evolving environments, where continuous adaptation causes abrupt erosion of historical knowledge. This paper proposes Federated Exponential Moving Average (FedEMA), a novel framework that addresses this challenge through two integral innovations: (I) Server-side model's historical fitting capability preservation via fusing current FL round's aggregation model and a proposed previous FL round's exponential moving average (EMA) model; (II) Vehicle-side negative entropy regularization to prevent FL models' possible overfitting to EMA-introduced temporal patterns. Above two strategies empower FedEMA a dual-objective optimization that balances model generalization and adaptability. In addition, we conduct theoretical convergence analysis for the proposed FedEMA. Extensive experiments both on Cityscapes dataset and Camvid dataset demonstrate FedEMA's superiority over existing approaches, showing 7.12% higher mean Intersection-over-Union (mIoU).

Wei-Bin Kou、Guangxu Zhu、Bingyang Cheng、Shuai Wang、Ming Tang、Yik-Chung Wu

自动化技术、自动化技术设备计算技术、计算机技术

Wei-Bin Kou,Guangxu Zhu,Bingyang Cheng,Shuai Wang,Ming Tang,Yik-Chung Wu.FedEMA: Federated Exponential Moving Averaging with Negative Entropy Regularizer in Autonomous Driving[EB/OL].(2025-05-01)[2025-06-05].https://arxiv.org/abs/2505.00318.点此复制

评论