Peifeng Zhang — accepted AI-conference papers

2026

SAGE: Style-Adaptive Generalization for Privacy-Constrained Semantic Segmentation Across Domains

Qingmei Li, Yang Zhang, Peifeng Zhang, Haohuan Fu, Juepeng Zheng

CVPR 2026

Domain generalization for semantic segmentation aims to mitigate the degradation in model performance caused by domain shifts. However, in many real-world scenarios, we are unable to access the model parameters and architectural details due to privacy concerns and security constraints. Traditional f

Cited by 0 Source ↗Scholar ↗

2025

Towards Personalized Federated Learning via Contrastive-Augmented Local Memorization Retrieval

Peifeng Zhang, Jiahui Chen

ICASSP 2025accepted

Federated learning (FL) enables clients to collaboratively train statistical models while maintaining the privacy of their local data. However, traditional FL methods often suffer performance degradation due to data heterogeneity across clients. To mitigate this issue, we propose an efficient person…

Cited by 0 Source ↗Scholar ↗