Xin Ye
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Xin Ye has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Jinjie Zhong
Department of Obstetrics of the Second Affiliated Hospital, and Department of Basic Medicine Sciences Zhejiang University School of Medicine Hangzhou Zhejiang China
2 shared publications - Lin-Lin Wang
Department of Orthopaedics of Sir Run Run Shaw Hospital, and Department of Basic Medicine Sciences Zhejiang University School of Medicine Hangzhou Zhejiang China
2 shared publications Lvwan Xu
Department of Basic Medicine Sciences, and Department of Orthopaedics of Sir Run Run Shaw Hospital Zhejiang University School of Medicine Hangzhou China
2 shared publications- Xiang Tian
Zhejiang Provincial Key Laboratory of Internet Multimedia Technology, College of Biomedical Engineering & Instrument Science, Zhejiang University, Hangzhou 310027, China
2 shared publications - Yaowu Chen
Zhejiang University
2 shared publications - Ying-Ying Chen
Department of Obstetrics of the Second Affiliated Hospital and Department of Basic Medicine Sciences, Zhejiang University School of Medicine, Hangzhou 310009, PR China
2 shared publications
Latest Publications
- Open Access
- 10 May 2024
- Published by Springer Nature in Neural Processing Letters
- Vol. 56 (3) , 1-25
A Unified Asymmetric Knowledge Distillation Framework for Image Classification
Knowledge distillation is a model compression technique that transfers knowledge learned by teacher networks to student networks. Existing knowledge distillation methods greatly expand the forms of knowledge, but also make the distillation models complex and symmetric. However, few studies have explored the commonalities among these methods. In this study, we propose a concise distillation framework to unify these methods and a method to construct asymmetric knowledge distillation under the framework. Asymmetric distillation aims to enable differentiated knowledge transfers for different distillation objects. We designed a multi-stage shallow-wide branch bifurcation method to distill different knowledge representations and a grouping ensemble strategy to supervise the network to teach and learn selectively. Consequently, we conducted experiments using image classification benchmarks to verify the proposed method. Experimental results show that our implementation can achieve considerable improvements over existing methods, demonstrating the effectiveness of the method and the potential of the framework.
- 10 May 2024
- Published by Springer Nature in Neural Processing Letters
- Vol. 56 (3) , 1-25
Open AccessA Unified Asymmetric Knowledge Distillation Framework for Image Classification
Knowledge distillation is a model compression technique that transfers knowledge learned by teacher networks to student networks. Existing knowledge distillation methods greatly expand the forms of knowledge, but also make the distillation models complex and symmetric. However, few studies have explored the commonalities among these methods. In this study, we propose a concise distillation framework to unify these methods and a method to construct asymmetric knowledge distillation under the framework. Asymmetric distillation aims to enable differentiated knowledge transfers for different distillation objects. We designed a multi-stage shallow-wide branch bifurcation method to distill different knowledge representations and a grouping ensemble strategy to supervise the network to teach and learn selectively. Consequently, we conducted experiments using image classification benchmarks to verify the proposed method. Experimental results show that our implementation can achieve considerable improvements over existing methods, demonstrating the effectiveness of the method and the potential of the framework.
- 30 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 31 (10709908) , 566-570
Knowledge Distillation via Multi-Teacher Feature Ensemble
This letter proposes a novel method for effectively utilizing multiple teachers in feature-based knowledge distillation. Our method involves a multi-teacher feature ensemble module for generating a robust feature ensemble and a student-teacher mapping module for bridging the student feature and ensemble feature. In addition, we utilize separate optimization, where the student's feature extractor is optimized under distillation supervision while its classifier is obtained through classifier reconstruction. We evaluate our method on the CIFAR-100, ImageNet and MS-COCO datasets, and the experimental results demonstrate its effectiveness.
- 30 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 31 (10709908) , 566-570
Knowledge Distillation via Multi-Teacher Feature Ensemble
This letter proposes a novel method for effectively utilizing multiple teachers in feature-based knowledge distillation. Our method involves a multi-teacher feature ensemble module for generating a robust feature ensemble and a student-teacher mapping module for bridging the student feature and ensemble feature. In addition, we utilize separate optimization, where the student's feature extractor is optimized under distillation supervision while its classifier is obtained through classifier reconstruction. We evaluate our method on the CIFAR-100, ImageNet and MS-COCO datasets, and the experimental results demonstrate its effectiveness.
- 9 March 2023
- Published by Springer Nature in Neural Processing Letters
- Vol. 55 (7) , 9085-9100
Rethinking the Value of Local Feature Fusion in Convolutional Neural Networks
- 9 March 2023
- Published by Springer Nature in Neural Processing Letters
- Vol. 55 (7) , 9085-9100
Rethinking the Value of Local Feature Fusion in Convolutional Neural Networks
- Open Access
- 29 June 2021
- Published by Wiley in Cell Proliferation
- Vol. 54 (8) , e13092
T‐cell infiltration, contribution and regulation in the central nervous system post‐traumatic injury
T cells participate in the repair process and immune response in the CNS post‐traumatic injury and play both a beneficial and harmful role. Together with nerve cells and other immune cells, they form a microenvironment in the CNS post‐traumatic injury. The repair of traumatic CNS injury is a long‐term process. T cells contribute to the repair of the injury site to influence the recovery. Recently, with the advance of new techniques, such as mass spectrometry‐based flow cytometry, modern live‐cell imaging, etc, research focusing on T cells is becoming one of the valuable directions for the future therapy of traumatic CNS injury. In this review, we summarized the infiltration, contribution and regulation of T cells in post‐traumatic injury, discussed the clinical significance and predicted the future research direction.
- 29 June 2021
- Published by Wiley in Cell Proliferation
- Vol. 54 (8) , e13092
Open AccessT‐cell infiltration, contribution and regulation in the central nervous system post‐traumatic injury
T cells participate in the repair process and immune response in the CNS post‐traumatic injury and play both a beneficial and harmful role. Together with nerve cells and other immune cells, they form a microenvironment in the CNS post‐traumatic injury. The repair of traumatic CNS injury is a long‐term process. T cells contribute to the repair of the injury site to influence the recovery. Recently, with the advance of new techniques, such as mass spectrometry‐based flow cytometry, modern live‐cell imaging, etc, research focusing on T cells is becoming one of the valuable directions for the future therapy of traumatic CNS injury. In this review, we summarized the infiltration, contribution and regulation of T cells in post‐traumatic injury, discussed the clinical significance and predicted the future research direction.
- Open Access
- 23 March 2021
- Published by Frontiers Media SA in Frontiers in Neuroscience
- Vol. 15
New Insight of Circular RNAs' Roles in Central Nervous System Post-Traumatic Injury
The central nervous system (CNS) post-traumatic injury can cause severe nerve damage with devastating consequences. However, its pathophysiological mechanisms remain vague. There is still an urgent need for more effective treatments. Circular RNAs (circRNAs) are non-coding RNAs that can form covalently closed RNA circles. Through second-generation sequencing technology, microarray analysis, bioinformatics, and other technologies, recent studies have shown that a number of circRNAs are differentially expressed after traumatic brain injury (TBI) or spinal cord injury (SCI). These circRNAs play important roles in the proliferation, inflammation, and apoptosis in CNS post-traumatic injury. In this review, we summarize the expression and functions of circRNAs in CNS in recent studies, as well as the circRNA–miRNA–mRNA interaction networks. The potential clinical value of circRNAs as a therapeutic target is also discussed.
- 23 March 2021
- Published by Frontiers Media SA in Frontiers in Neuroscience
- Vol. 15
Open AccessNew Insight of Circular RNAs' Roles in Central Nervous System Post-Traumatic Injury
The central nervous system (CNS) post-traumatic injury can cause severe nerve damage with devastating consequences. However, its pathophysiological mechanisms remain vague. There is still an urgent need for more effective treatments. Circular RNAs (circRNAs) are non-coding RNAs that can form covalently closed RNA circles. Through second-generation sequencing technology, microarray analysis, bioinformatics, and other technologies, recent studies have shown that a number of circRNAs are differentially expressed after traumatic brain injury (TBI) or spinal cord injury (SCI). These circRNAs play important roles in the proliferation, inflammation, and apoptosis in CNS post-traumatic injury. In this review, we summarize the expression and functions of circRNAs in CNS in recent studies, as well as the circRNA–miRNA–mRNA interaction networks. The potential clinical value of circRNAs as a therapeutic target is also discussed.