田冠中助理研究员、博士、硕士生导师
研究中心:控制分院
研究领域:神经网络轻量化、计算机视觉
电话:
电子邮箱:gztian@zju.edu.cn
办公地址:浙江省宁波市鄞州区学府路5号
个人简介

田冠中,浙江大学宁波研究院、浙江大学控制与工程学院助理研究员,硕士生导师,入选宁波市“甬江引才工程”青年创新个人,宁波市拔尖人才。本科毕业于哈尔滨工业大学自动化专业,获学士学位,2021年获浙江大学控制科学与工程专业博士学位,期间获浙江大学资助赴美国加州大学默塞德分校进行联合培养。

长期从事机器感知、计算机视觉、具身智能等方面的研究。主持主持国家自然科学基金委青年科学基金项目,宁波市青年博士创新项目,工业控制国家实验室开放课题。作为课题骨干参与国家重点研发计划、国家自然科学基金、浙江省自然科学基金、企事业单位委托等多项科研项目。获智能机器人与系统国际会议(IROS)机器人建造大赛冠军,浙江省科学技术进步三等奖。IEEE TIP、TNNLS、TCSVT、CVPR、ECCV、BMVC等领域内重要国际期刊/会议上发表论文20余篇现任国际期刊《Journal of Intelligent Manufacturing and Special Equipment》青年编委担任人工智能顶级会议CVPR,ECCV,BMVC和人工智能高水平期刊TNNLS,Neurocomputing,Neural Computing and Applications审稿人。

 

科研情况

1.项目研究

1. 《面向移动机器人的深度模型稀疏化关键理论与可解释性研究》,纵向项目,国家自然科学基金委青年科学基金项目,62303405,30万,2024.1-2026.12,1/1.

2. 《深度神经网络稀疏化的可解释性研究与应用》,纵向项目,宁波市自然科学基金青年博士创新研究项目,2023J40,20万,2023.6-2026.6,1/1.

3. 复杂作业环境的农机智能系统和大数据智能管理平台》,纵向项目,宁波市科技创新2025 重大专项,20231ZDYF020164,250万,2023.3-2026.2, 11/29.

4. 《工业巡检智能检测算法模型部署 》,横向项目,企业课题,NBKZ2024H0006,13万,2023.9-2023.11, 1/1.

5. 《工业缺陷检测算法模型研发 》,横向项目,企业课题,NBKZ2024H0014 ,30万,2024.2-2026.6, 1/1.

6. 《基于深度模型的复杂零部件智能视觉检测关键技术与装备》,人才项目,宁波市甬江人才工程,2022A-233-G,100万,2023.1-2027.1,1/1


2. 论文、著作

1. Guanzhong Tian#, Yiran Sun, Yuang Liu, Xianfang Zeng, Mengmeng Wang, Yong Liu, Jiangning Zhang, Jun Chen. Adding Before Pruning: Sparse Filter Fusion for Deep Convolutional Neural Networks via Auxiliary Attention, IEEE Transactions on Neural Networks and Learning Systems(TNNLS),2021, Early Access.SCI一区TOP,IF=14.255,他引6次)

2. Jun Chen, Shipeng Bai, Tianxin Huang, Mengmeng Wang, Guanzhong Tian*,Yong Liu*. Data-Free Quantization via Mixed-Precision Compensation without Fine-Tuning, Pattern Recognition. (PR), 2023: 109780.(SCI一区TOP,IF=8,他引3次)

3. Guanzhong Tian#, Jun Chen, Xianfang Zeng, Yong Liu. Pruning by Training: A novel Deep Neural Network Compression Framework for Image Processing, IEEE Signal Processing LettersSPL), 2021,28:344-348. (SCI二区,IF=3.109,他引21)

4. Yuhu Bai, Jiangning Zhang, Zhaofeng Chen, Yuhang Dong, Yunkang Cao, Guanzhong Tian*. Dual-path Frequency Discriminators for Few-shot Anomaly Detection, Knowledge-Based Systems, 2024. (SCI一区TOP,IF=7.2)

5. Siqi Li, Jun Chen, Shanqi Liu, Chengrui Zhu, Guanzhong Tian*, Yong Liu*. MCMC: Multi-Constrained Model Compression via One-Stage Envelope Reinforcement Learning,IEEE Transactions on Neural Networks and Learning Systems, 2024. (SCI一区TOP,IF=10.2)

6. Haoyang He, Zhishan Li, Guanzhong Tian*, Hongxu Chen, Lei Xie*, Shan Lu, Hongye Su. Towards Accurate Dense Pedestrian Detection via Occlusion-prediction Aware Label Assignment and Hierarchical-NMS[J]. Pattern Recognition Letters, 2023.(SCI二区,IF=5)

7. Zetao Xia &,Yining Wang, Longhua Ma, Yang Zhu, Yongjie Li, Jili Tao, Guanzhong Tian*. A Hybrid Prognostic Method for Proton-Exchange-Membrane Fuel Cell with Decomposition Forecasting Framework Based on AEKF and LSTM, Sensors, 2022, 23(1), 166. (SCI三区,IF=3.9,他引4)

8. Yingqing Yang, Guanzhong Tian*, Mingyuan Liu, Yihao Chen, Jun Chen, Yong Liu, Yu Pan, Longhua Ma.Pse: mixed quantization framework of neural networks for efficient deployment, Journal of Real-Time Image Processing, 2023. (SCI四区,IF=2.9)

9. Yihao Chen&, Zhishan Li, Yingqing Yang, Lei Xie, Yong Liu, Longhua Ma, Shanqi Liu, Guanzhong Tian*. CICC: Channel Pruning via the Concentration of Information and Contributions of Channels, The 33rd British Machine Vision Conference(BMVC), 2022. (CCF C国际会议)

10. Ruoyu Wu, Guanzhong Tian*, Longhua Ma, Zhishan Li, Shanqi Liu. Lightweight Cryptography Implementation for Internet of Things Network on FPGA,2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC) (CCF C国际会议)

11. Juntao Jiang, Xiyu Chen, Guanzhong Tian*, Yong Liu*. ViG-UNet: Vision Graph Neural Networks for Medical Image Segmentation,2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI), 1-5.

12. Mengmeng Wang, Jianbiao Mei, Liang Liu, Guanzhong Tian, Yong Liu, Zaisheng Pan, Delving Deeper Into Mask Utilization in Video Object Segmentation,  IEEE Transactions on Image Processing(TIP), vol. 31, pp. 6255-6266, 2022.

13. Chao Xu, Jiangning Zhang, Yue Han, Guanzhong Tian, Xianfang Zeng, Ying Tai, Yabiao Wang, Chengjie Wang, and Yong Liu. Designing one unified framework forhigh-fidelity face reenactment andswapping, European Conference on Computer Vision (ECCV), 54-71, 2022.

14.  Chao Xu, Jiangning Zhang, Mengmeng Wang, Guanzhong Tian, Yong Liu, Multilevel Spatial-Temporal Feature Aggregation for Video Object Detection,  IEEE Transactions on Circuits and Systems for Video Technology(TCSVT), vol. 32, no. 11, pp. 7809-7820,  2022.

15. Ruoyu Wu, Ming Xu, Yingqing Yang, Guanzhong Tian, Ping Yu, Yangfan Zhao, Bin Lian, Longhua Ma, Efficient High-Radix GF(p) Montgomery Modular Multiplication via Deep Use Of Multipliers, IEEE Transactions on Circuits and Systems II: Express Briefs, 2022, doi: 10.1109/TCSII.2022.3197314.

16. Xianfang Zeng, Yusu Pan, Hao Zhang, Mengmeng Wang, Guanzhong Tian, Yong Liu. Unpaired salient object translation via spatial attention prior, Neurocomputing, 2020.

17. Xianfang Zeng, Wenxuan Wu, Guanzhong Tian, Fuxin Li, and Yong Liu. Deep Superpixel Convolutional Network for Image Recognition. IEEE Signal Processing Letters(SPL),2021. 

18. Zhishan Li, Yiran Sun, Guanzhong Tian, Lei Xie, Yong Liu, Hongye Su, Yifan He. A compression pipeline for one-stage object detection model, Journal of Real-Time Image Processing (2021): 1-14.

19. Liu, Shanqi, Weiwei Liu, Wenzhou Chen, Guanzhong Tian, Jun Chen, Yao Tong, Junjie Cao, Yong Liu. Learning Multi-Agent Cooperation via Considering Actions of Teammates. IEEE Transactions on Neural Networks and Learning Systems,2023.

20. Zetao Xia, Yining Wang, Guanzhong Tian, Longhua Ma, Ming Xu. Fast Fault Diagnosis for Proton Exchange Membrane Fuel Cells based on an Electrochemical Impedance Spectroscopy Measurement[C]//2022 China Automation Congress (CAC). IEEE, 2022: 2257-2262.

 

3. 成果奖项

1. 2024年度智能机器人与系统国际会议(IROS)机器人建造大赛,冠军

2. 2023年度浙江省科学技术进步三等奖,“大规模电梯智能化运维动态监测关键技术及应用


4.发明专利

1. 一种基于多教师模型的知识蒸馏方法, 发明专利,中国,202410834565.3, 2024/08/01, 1/5.

2. 一种基于基础模型的单域泛化方法,发明专利,中国,202410822182.4, 2024/08/19, 1/6.


5.教学与课程

1. 计算机视觉(研究生专业课)

2. 机器视觉及应用(研究生专业课)

3. 高阶工程实践(研究生专业课)


关闭