田冠中(Guanzhong Tian)，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、神经网络模型轻量化等方面的研究。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。在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。
招生资格：硕士研究生
🔥 News
📝 Publications
2024
- Haoyang He, Yuhu Bai, Jiangning Zhang, Qingdong He, Hongxu Chen, Zhenye Gan, Chengjie Wang, Xiangtai Li, Guanzhong Tian, Lei Xie. Mambaad: Exploring state space models for multi-class unsupervised anomaly detection,arXiv,preprint,arXiv:2404.06564.
- Jiangning Zhang, Chengjie Wang, Xiangtai Li, Guanzhong Tian, Zhucun Xue, Yong Liu, Guansong Pang, Dacheng Tao. Learning Feature Inversion for Multi-class Anomaly Detection under General-purpose COCO-AD Benchmark,arXiv,preprint,arXiv:2404.10760,2024/4/16.
- Yuhu Bai, Jiangning Zhang, Yuhang Dong, Guanzhong Tian*, Yunkang Cao, Yabiao Wang, Chengjie Wang. Dual-path Frequency Discriminators for Few-shot Anomaly Detection,arXiv,preprint,arXiv:2403.04151.
- 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 (TNNLS).
2023
- 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. Pattern Recognition Letters, 2023.
- Jun Chen, Shipeng Bai, Tianxin Huang, Mengmeng Wang, Guanzhong Tian*,Yong Liu*. Data-Free Quantization via Mixed-Precision Compensation without Fine-Tuning, Pattern Recognition，2023: 109780 (PR).
- Shanqi Liu, 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, 2023/4/18 (TNNLS).
- Liang Liu , Boshen Zhang , Jiangning Zhang , Wuhao Zhang , Zhenye Gan, Guanzhong Tian , Wenbing Zhu , Yabiao Wang , Chengjie Wang. MixTeacher: Mining Promising Labels with Mixed Scale Teacher for Semi-Supervised Object Detection, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR23).
- Xuhai Chen, Jiangning Zhang, Guanzhong Tian, Haoyang He, Wuhao Zhang, Yabiao Wang, Chengjie Wang, Yunsheng Wu, Yong Liu. Clip-ad: A language-guided staged dual-path model for zero-shot anomaly detection,arXiv,preprint,arXiv:2311.00453.
- Ruoyu Wu, Guanzhong Tian, Longhua Ma, Zhishan Li, Shanqi Liu. Efficient High-Radix GF (p) Montgomery Modular Multiplication Via Deep Use Of Multipliers 2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC).
- 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).
2022
- 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 British Machine Vision Conference (BMVC 2022).
- Mengmeng Wang, Jianbiao Mei, Lina Liu, Guanzhong Tian, Yong Liu, Zaisheng Pan. Delving deeper into mask utilization in video object segmentation 2022/9/27 IEEE Transactions on Image Processing (TIP).
2021
- 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,2021. (TNNLS).
- Guanzhong Tian, Jun Chen, Xianfang Zeng, Yong Liu. Pruning by Training: A novel Deep Neural NetworkCompression Framework for Image Processing, IEEE Signal Processing Letters, 2021.
- Xianfang Zeng, Wenxuan Wu, Guangzhong Tian, Fuxin Li, and Yong Liu. Deep Superpixel Convolutional Network for Image Recognition. IEEE Signal Processing Letters，2021.
- 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. Springer.
2020
- Xianfang Zeng, Yusu Pan, Hao Zhang, Mengmeng Wang, Guanzhong Tian, Yong Liu. Unpaired salient object translation via spatial attention prior, Neurocomputing, 2020.
- Jong-Hyok Ri#, Guanzhong Tian#, Yong Liu, Wei-hua Xu, Jun-gang Lou. Extreme learning machine with hybrid cost function of G-mean and probability for imbalance learning, International Journal of Machine Learning and Cybernetics, 2020, 11(9): 2007-2020.
2019
- Guanzhong Tian, Yi Yuan, Yong Liu. Audio2face: Generating speech/face animation from single audio with attention-based bidirectional lstm networks, 2019 IEEE international conference on Multimedia & Expo Workshops.
- Guanzhong Tian, Liang Liu, JongHyok Ri, Yong Liu, Yiran Sun. ObjectFusion: An object detection and segmentation framework with RGB-D SLAM and convolutional neural networks, Neurocomputing, 2019, 345: 3-14.
📖 Educations
- 2010. Bachelor Harbin Institute of Technology, Harbin, China
- 2021. PhD. Zhejiang University, Hangzhou, China
- Joint learning University of California, Merced
📖 教学与课程
- 计算机视觉（研究生专业课）
- 机器视觉及应用（研究生专业课）
- 高阶工程实践 （研究生公共课）
💻 工作研究项目
- 国家自然科学基金委青年科学基金项目，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，62303405，主持.
- 宁波市自然科学基金青年博士创新研究项目，深度神经网络稀疏化的可解释性研究与应用，2023J40，主持.
- 工业控制国家实验室开放课题，小数据条件下基于深度网络模型的端到端工业视觉检测，ICT2022B31， 主持.
- 宁波市甬江人才工程青年创新人才项目，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，主持.
- 国家重点研发计划课题，2018YFB1702203，网络协同制造和智能工厂，参与.
- 国家重点研发计划课题，2018AAA0101503，大电网调控人在回来混合增强学习方法研究，参与.
- 企业委托科研，AI机器视觉智能型自动扶梯，项目负责人