EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

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

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

Electronics · 24.05.2025 · 14 (11) · 2147

DOI: 10.3390/electronics14112147 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 24.05.2025. Verfasst von Qi Cui und 7 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Open Topics from the Lion Rock Labs of Cyberspace Security, Natural Science Basic Research Program of Shaanxi, Fundamental Research Funds for the Central Universities, China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Förderung

  • Open Topics from the Lion Rock Labs of Cyberspace Security
  • Natural Science Basic Research Program of Shaanxi
  • Fundamental Research Funds for the Central Universities, China
  • Guangdong S&T Program: Guangdong Provincial Key Laboratory of Automotive Electrical and Electronic Architecture (2023)

Zitieren

APA

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

Vancouver

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

BibTeX
@article{Cui2025,
  author = {Cui, Qi and Sun, Lin and Zhou, Yilin and Pan, Ke and Du, Peng and Xu, Wei and Wang, Daihan and Sheng, Kai},
  title = {FedSS: A High-Efficiency Federated Learning Method for Semantic Segmentation},
  journal = {Electronics},
  year = {2025},
  volume = {14},
  number = {11},
  pages = {2147},
  doi = {10.3390/electronics14112147}
}
Kostenlos starten →