Yirui Zhou
Yirui Zhou has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Yangchun Zhang
School of Mathematics, Harbin Institute of Technology, Harbin, China
5 shared publications - Mengxiao Lu
Department of Mathematics, College of Sciences, Shanghai University, Shanghai, 200444, China
3 shared publications - Xiaowei Liu
Department of Mathematics, College of Sciences, Shanghai University, Shanghai, 200444, China
3 shared publications - Yaxin Peng
Shanghai University, Shanghai, China
3 shared publications - Zhiyuan Xu
Midea Group, Shanghai, China
3 shared publications - Jian Tang
Midea Group, Shanghai, China
2 shared publications
Latest Publications
- Open Access
- 14 July 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (14) , 2352
Fed-RSAdapter: Federated Fine-Tuning of Remote Sensing Images via Multi-Scale Adapter Modules
In edge computing scenarios for remote sensing image interpretation, two fundamental challenges constrain the effectiveness of federated fine-tuning: the limited computational capacity of edge devices restricts the multi-scale feature learning capability of lightweight deployed models, while the highly heterogeneous and imbalanced data distributions (Non-IID settings) across clients render conventional parameter aggregation strategies ineffective. To address these challenges jointly, this paper proposes Fed-RSAdapter, a federated fine-tuning framework for remote sensing imagery based on multi-scale adapter modules. On the edge side, a multi-scale adapter architecture with cross-layer dense connections and feature map concatenation alignment is introduced. By inserting lightweight adapter modules in parallel within a frozen backbone, the proposed design captures multi-scale spatial characteristics inherent in high-resolution remote sensing imagery while confining trainable parameters to less than 5% of the full model, thereby satisfying strict on-device computational and communication constraints. On the server side, a parameter similarity-aware aggregation strategy is designed to handle client heterogeneity. Client adapter parameters are normalized and mapped into a similarity matrix via Gaussian kernel distance, enabling the server to perform personalized weighted aggregation that balances global generalization with client-specific adaptation. Extensive experiments on scene classification, object detection, and semantic segmentation benchmarks demonstrate that Fed-RSAdapter achieves an average improvement of 3.75% in overall accuracy for scene classification, 0.74% in mAP for object detection, and 0.25% in overall accuracy for semantic segmentation over federated baselines, while reducing the volume of transmitted parameters to approximately 4.93% of that required by conventional full-parameter federated learning. These results demonstrate the communication-efficient fine-tuning capability of the proposed framework under federated remote sensing settings. We further clarify that actual deployment on embedded edge hardware is not directly evaluated in this work and is therefore treated as an important direction for future validation rather than an experimentally proven conclusion.
- 14 July 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (14) , 2352
Open AccessFed-RSAdapter: Federated Fine-Tuning of Remote Sensing Images via Multi-Scale Adapter Modules
In edge computing scenarios for remote sensing image interpretation, two fundamental challenges constrain the effectiveness of federated fine-tuning: the limited computational capacity of edge devices restricts the multi-scale feature learning capability of lightweight deployed models, while the highly heterogeneous and imbalanced data distributions (Non-IID settings) across clients render conventional parameter aggregation strategies ineffective. To address these challenges jointly, this paper proposes Fed-RSAdapter, a federated fine-tuning framework for remote sensing imagery based on multi-scale adapter modules. On the edge side, a multi-scale adapter architecture with cross-layer dense connections and feature map concatenation alignment is introduced. By inserting lightweight adapter modules in parallel within a frozen backbone, the proposed design captures multi-scale spatial characteristics inherent in high-resolution remote sensing imagery while confining trainable parameters to less than 5% of the full model, thereby satisfying strict on-device computational and communication constraints. On the server side, a parameter similarity-aware aggregation strategy is designed to handle client heterogeneity. Client adapter parameters are normalized and mapped into a similarity matrix via Gaussian kernel distance, enabling the server to perform personalized weighted aggregation that balances global generalization with client-specific adaptation. Extensive experiments on scene classification, object detection, and semantic segmentation benchmarks demonstrate that Fed-RSAdapter achieves an average improvement of 3.75% in overall accuracy for scene classification, 0.74% in mAP for object detection, and 0.25% in overall accuracy for semantic segmentation over federated baselines, while reducing the volume of transmitted parameters to approximately 4.93% of that required by conventional full-parameter federated learning. These results demonstrate the communication-efficient fine-tuning capability of the proposed framework under federated remote sensing settings. We further clarify that actual deployment on embedded edge hardware is not directly evaluated in this work and is therefore treated as an important direction for future validation rather than an experimentally proven conclusion.
- 11 February 2026
- Published by Elsevier in Applied Soft Computing
- Vol. 193
Tackling value estimation bias in successor features by distributional reinforcement learning
- 11 February 2026
- Published by Elsevier in Applied Soft Computing
- Vol. 193
Tackling value estimation bias in successor features by distributional reinforcement learning
- 14 July 2024
- Published by Elsevier in Knowledge-Based Systems
- Vol. 300
Generalization error for portable rewards in transfer imitation learning
- 14 July 2024
- Published by Elsevier in Knowledge-Based Systems
- Vol. 300
Generalization error for portable rewards in transfer imitation learning
- 25 May 2023
- Published by Elsevier in Neural Networks
- Vol. 165, 43-59
Distributional generative adversarial imitation learning with reproducing kernel generalization
- 25 May 2023
- Published by Elsevier in Neural Networks
- Vol. 165, 43-59
Distributional generative adversarial imitation learning with reproducing kernel generalization
- 13 September 2022
- Published by Elsevier in Computational Statistics & Data Analysis
- Vol. 178
Applications on linear spectral statistics of high-dimensional sample covariance matrix with divergent spectrum
- 13 September 2022
- Published by Elsevier in Computational Statistics & Data Analysis
- Vol. 178
Applications on linear spectral statistics of high-dimensional sample covariance matrix with divergent spectrum
- 14 August 2022
- Published by Springer Nature
- p. 385-399
Generalization and Computation for Policy Classes of Generative Adversarial Imitation Learning
- 14 August 2022
- Published by Springer Nature
- p. 385-399
Generalization and Computation for Policy Classes of Generative Adversarial Imitation Learning