Weiyu Sun

Weiyu Sun

Auto-generated profile, based on publicly available information

Weiyu Sun

School of Electronic Science and Engineering, Nanjing University, Nanjing, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
30 May 2024 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
XZXinyu Zhang
Xinyu Zhang
WSWeiyu Sun
Weiyu Sun
HLHao Lu
Hao Lu
YCYing Chen
Ying Chen
YGYun Ge
Yun Ge
YCYingcong Chen
Yingcong Chen
Remote photoplethysmography (rPPG) is a non-invasive technique that aims to capture subtle variations in facial pixels caused by changes in blood volume resulting from cardiac activities. Most existing unsupervised methods for rPPG tasks focus on the contrastive learning between samples while neglecting the inherent self-similarity prior in physiological signals. In this paper, we propose a Self-Similarity Prior Distillation (SSPD) framework for unsupervised rPPG estimation, which capitalizes on the intrinsic temporal self-similarity of cardiac activities. Specifically, we first introduce a physical-prior embedded augmentation technique to mitigate the effect of various types of noise. Then, we tailor a self-similarity-aware network to disentangle more reliable self-similar physiological features. Finally, we develop a hierarchical self-distillation paradigm for self-similarity-aware learning and rPPG signal decoupling. Comprehensive experiments demonstrate that the unsupervised SSPD framework achieves comparable or even superior performance compared to the state-of-the-art supervised methods. Meanwhile, SSPD has the lowest inference time and computation cost among end-to-end models.

17 July 2024 in IEEE Signal Processing Letters
Verified
Journal Article
Closed access
XZXinyu Zhang
Xinyu Zhang
WSWeiyu Sun
Weiyu Sun
YCYing Chen
Ying Chen
Federated learning (FL) is a privacy-preserving paradigm for collaboratively training a global model from decentralized clients. However, the performance of FL is hindered by non-independent and identically distributed (non-IID) data and device heterogeneity. In this letter, we revisit this key challenge through the lens of gradient conflicts on the server side. Specifically, we first investigate the gradient conflict phenomenon among multiple clients and reveal that stronger heterogeneity leads to more severe gradient conflicts. To tackle this issue, we propose FedGH, a simple yet effective method that mitigates local drifts through Gradient Harmonization. This technique projects one gradient vector onto the orthogonal plane of the other within conflicting client pairs. Extensive experiments demonstrate that FedGH consistently enhances multiple state-of-the-art FL baselines across diverse benchmarks and non-IID scenarios. Moreover, FedGH yields more significant improvements in scenarios with stronger heterogeneity. As a plug-and-play module, FedGH can seamlessly integrate into any FL framework without requiring hyperparameter tuning.

26 October 2023
Verified
Conference Paper
Open access
WSWeiyu Sun
Weiyu Sun
XZXinyu Zhang
Xinyu Zhang
HLHao Lu
Hao Lu
YCYing Chen
Ying Chen
YGYun Ge
Yun Ge
YCYingcong Chen
Yingcong Chen

12 October 2026 in Knowledge-Based Systems
Verified
Journal Article
Open access
LCLiangliang Chen
Liangliang Chen
WSWeiyu Sun
Weiyu Sun
HXHuiru Xie
Huiru Xie
YCYongnuo Cai
Yongnuo Cai
YZYing Zhang
Ying Zhang