Shiyang Yan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Shiyang Yan has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Chao Wu
School of Public Affairs, Zhejiang University, Hangzhou 310058, China
1 shared publication Jialie Shen
1 shared publication- Jun Xu
Nanjing Institute of Advanced Artificial Intelligence
1 shared publication Lin Xu
1 shared publication- Lin Xu
Nanjing Institute of Advanced Artificial Intelligence
1 shared publication - Ruijie Hou
Zhejiang University
1 shared publication
Latest Publications
- Open Access
- 5 April 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in TechRxiv
LM-Metric: Learned Pair Weighting and Contextual Memory for Deep Metric Learning
Learned Pair Weighting and Contextual Memory for Deep Metric Learning.
- 5 April 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in TechRxiv
Open AccessLM-Metric: Learned Pair Weighting and Contextual Memory for Deep Metric Learning
Learned Pair Weighting and Contextual Memory for Deep Metric Learning.
- Open Access
- 12 May 2022
- Published by MDPI AG in Electronics
- Vol. 11 (10) , 1548
Efficient Ring-Topology Decentralized Federated Learning with Deep Generative Models for Medical Data in eHealthcare Systems
By leveraging deep learning technologies, data-driven-based approaches have reached great success with the rapid increase of data generated for medical applications. However, security and privacy concerns are obstacles for data providers in many sensitive data-driven scenarios, such as rehabilitation and 24 h on-the-go healthcare services. Although many federated learning (FL) approaches have been proposed with DNNs for medical applications, these works still suffer from low usability of data due to data incompleteness, low quality, insufficient quantity, sensitivity, etc. Therefore, we propose a ring-topology-based decentralized federated learning (RDFL) scheme for deep generative models (DGM), where DGM is a promising solution for solving the aforementioned data usability issues. Our RDFL schemes provide communication efficiency and maintain training performance to boost DGMs in target tasks compared with existing FL works. A novel ring FL topology and a map-reduce-based synchronizing method are designed in the proposed RDFL to improve the decentralized FL performance and bandwidth utilization. In addition, an inter-planetary file system (IPFS) is introduced to further improve communication efficiency and FL security. Extensive experiments have been taken to demonstrate the superiority of RDFL with either independent and identically distributed (IID) datasets or non-independent and identically distributed (Non-IID) datasets.
- 12 May 2022
- Published by MDPI AG in Electronics
- Vol. 11 (10) , 1548
Open AccessEfficient Ring-Topology Decentralized Federated Learning with Deep Generative Models for Medical Data in eHealthcare Systems
By leveraging deep learning technologies, data-driven-based approaches have reached great success with the rapid increase of data generated for medical applications. However, security and privacy concerns are obstacles for data providers in many sensitive data-driven scenarios, such as rehabilitation and 24 h on-the-go healthcare services. Although many federated learning (FL) approaches have been proposed with DNNs for medical applications, these works still suffer from low usability of data due to data incompleteness, low quality, insufficient quantity, sensitivity, etc. Therefore, we propose a ring-topology-based decentralized federated learning (RDFL) scheme for deep generative models (DGM), where DGM is a promising solution for solving the aforementioned data usability issues. Our RDFL schemes provide communication efficiency and maintain training performance to boost DGMs in target tasks compared with existing FL works. A novel ring FL topology and a map-reduce-based synchronizing method are designed in the proposed RDFL to improve the decentralized FL performance and bandwidth utilization. In addition, an inter-planetary file system (IPFS) is introduced to further improve communication efficiency and FL security. Extensive experiments have been taken to demonstrate the superiority of RDFL with either independent and identically distributed (IID) datasets or non-independent and identically distributed (Non-IID) datasets.
- Open Access
HorNet: A Hierarchical Offshoot Recurrent Network for Improving Person Re-ID via Image Captioning
Person re-identification (re-ID) aims to recognize a person-of-interest across different cameras with notable appearance variance. Existing research works focused on the capability and robustness of visual representation. In this paper, instead, we propose a novel hierarchical offshoot recurrent network (HorNet) for improving person re-ID via image captioning. Image captions are semantically richer and more consistent than visual attributes, which could significantly alleviate the variance. We use the similarity preserving generative adversarial network (SPGAN) and an image captioner to fulfill domain transfer and language descriptions generation. Then the proposed HorNet can learn the visual and language representation from both the images and captions jointly, and thus enhance the performance of person re-ID. Extensive experiments are conducted on several benchmark datasets with or without image captions, i.e., CUHK03, Market-1501, and Duke-MTMC, demonstrating the superiority of the proposed method. Our method can generate and extract meaningful image captions while achieving state-of-the-art performance.
Open AccessHorNet: A Hierarchical Offshoot Recurrent Network for Improving Person Re-ID via Image Captioning
Person re-identification (re-ID) aims to recognize a person-of-interest across different cameras with notable appearance variance. Existing research works focused on the capability and robustness of visual representation. In this paper, instead, we propose a novel hierarchical offshoot recurrent network (HorNet) for improving person re-ID via image captioning. Image captions are semantically richer and more consistent than visual attributes, which could significantly alleviate the variance. We use the similarity preserving generative adversarial network (SPGAN) and an image captioner to fulfill domain transfer and language descriptions generation. Then the proposed HorNet can learn the visual and language representation from both the images and captions jointly, and thus enhance the performance of person re-ID. Extensive experiments are conducted on several benchmark datasets with or without image captions, i.e., CUHK03, Market-1501, and Duke-MTMC, demonstrating the superiority of the proposed method. Our method can generate and extract meaningful image captions while achieving state-of-the-art performance.