FedSS: A High-Efficiency Federated Learning Method for Semantic Segmentation

Cui, Qi; Sun, Lin; Zhou, Yilin; Pan, Ke; Du, Peng; Xu, Wei; Wang, Daihan; Sheng, Kai

doi:10.3390/electronics14112147

This is an early access version, the complete PDF, HTML, and XML versions will be available soon.

Open AccessArticle

FedSS: A High-Efficiency Federated Learning Method for Semantic Segmentation

by

Qi Cui

¹,

Lin Sun

²,

Yilin Zhou

²,

Ke Pan

^1,*,

Peng Du

¹,

Wei Xu

³,

Daihan Wang

³ and

Kai Sheng

²

¹

School of Cyber Engineering, Xidian University, Xi′an 710071, China

²

School of Guangzhou Institute of Technology, Xidian University, Guangzhou 510530, China

³

Guangzhou Automobile Group Co., Ltd., Guangzhou 511434, China

^*

Author to whom correspondence should be addressed.

Electronics 2025, 14(11), 2147; https://doi.org/10.3390/electronics14112147 (registering DOI)

Submission received: 15 April 2025 / Revised: 13 May 2025 / Accepted: 21 May 2025 / Published: 24 May 2025

Download Versions Notes

Abstract

Federated learning is a distributed machine learning framework that allows multiple clients to collaborate on training global models without sharing raw data, thereby protecting data privacy. However, it is still a challenge to construct an efficient federated learning method for the semantic segmentation task of automated driving street view. On the one hand, the complexity of the semantic segmentation model is high, resulting in huge computing and communication overhead of client local training. On the other hand, the client data distribution is significantly different and has Non-Independent and Identically Distributed(non-IID) characteristics, which easily leads to the difficulty of global model convergence or the deterioration of generalization performance. Therefore, this paper proposes a Federal Street View segmentation method, Federal Street View Segmentation(FedSS), which optimizes model training by improving the cross-entropy loss function and designing a gradient compensation strategy and a gradient sparse compression strategy to alleviate the high communication overhead in federation learning. Extensive experiments show that our approach can consume fewer computational resources and achieve higher communication efficiency while improving semantic segmentation performance.

Keywords: federated learning; semantic segmentation; communication efficiency; sparsity; data heterogeneity

Share and Cite

MDPI and ACS Style

Cui, Q.; Sun, L.; Zhou, Y.; Pan, K.; Du, P.; Xu, W.; Wang, D.; Sheng, K. FedSS: A High-Efficiency Federated Learning Method for Semantic Segmentation. Electronics 2025, 14, 2147. https://doi.org/10.3390/electronics14112147

AMA Style

Cui Q, Sun L, Zhou Y, Pan K, Du P, Xu W, Wang D, Sheng K. FedSS: A High-Efficiency Federated Learning Method for Semantic Segmentation. Electronics. 2025; 14(11):2147. https://doi.org/10.3390/electronics14112147

Chicago/Turabian Style

Cui, Qi, Lin Sun, Yilin Zhou, Ke Pan, Peng Du, Wei Xu, Daihan Wang, and Kai Sheng. 2025. "FedSS: A High-Efficiency Federated Learning Method for Semantic Segmentation" Electronics 14, no. 11: 2147. https://doi.org/10.3390/electronics14112147

APA Style

Cui, Q., Sun, L., Zhou, Y., Pan, K., Du, P., Xu, W., Wang, D., & Sheng, K. (2025). FedSS: A High-Efficiency Federated Learning Method for Semantic Segmentation. Electronics, 14(11), 2147. https://doi.org/10.3390/electronics14112147

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

FedSS: A High-Efficiency Federated Learning Method for Semantic Segmentation

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI