的个人主页 http://shi.buaa.edu.cn/07297/zh_CN/index.htm
个人简介:
工学博士,2002年至今任教于北京航空航天大学电子信息工程学院,博士生导师。长期从事信号采集与处理、图像识别、人工智能等相关理论和关键技术研究及模拟电子电路的教学工作。目前主要的研究方向为智能图像处理、空天地海大数据处理、深度学习、机器视觉等。围绕研究方向,开展国家自然科学基金、航空科学基金等项目的研究。获部级奖励2项。先后在英国曼彻斯特大学及美国匹兹堡大学进行访问研究。在国内外知名期刊与会议已发表论文70余篇,授权发明专利20余项。是国家教学团队和国家首届一流本科课程“电子电路1”核心成员。校研究生精品国际引智课程“编码理论”负责人,教学成果显著。出版专著1部。
研究方向:
嵌入式端高精实时目标智能检测算法研究
AI医学影像智能理解
AI大数据智能处理与分析
遥感图像智能理解
基于高效紧凑神经网络设计的图像识别技术
在研项目:
国家自然科学基金
北京市医院管理中心“登峰”计划专项
近三年(自2018年)代表性成果:
论文方面:
PUBLICATION:
[16] Qi Zhao, Xu Wang, Shuchang Lyu, Binghao Liu, Yifan Yang, A Feature Consistency Driven Attention Erasing Network for Fine-Grained Image Retrieval[J]. Pattern Recognition, 128:108618, 2022. (PR, SCI Q1, IF: 8.518)
[15] Yuewen Li, Wenquan Feng, Shuchang Lyu, Qi Zhao, Feature reconstruction and metric based network for few-shot object detection, Computer Vision and Image Understanding, 2022, 103600, ISSN 1077-3142, https://doi-org-443.e2.buaa.edu.cn/10.1016/j.cviu.2022.103600. (CVIU, SCI Q1, IF: 4.866)
[14] Shuchang Lyu, Binghao Liu, Qi Zhao, Yujing Ma, Lijiang Chen, A Similarity Distillation Guided Feature Refinement Network for Few-shot Semantic Segmentation[C]. International Conference on Image Processing, pp. 666-670, 2022. (ICIP)
[13] Linghan Cai, Meijing Wu, Lijiang Chen, Wenpei Bai, Min Yang, Shuchang Lyu, Qi Zhao, Using Guided Self-Attention with Local Information for Polyp Segmentation. Medical Image Computing and Computer Assisted Interventions, pp: 629-638, 2022. (MICCAI)
[12] Yuewwen li, Binghao Liu, Shuchang Lyu, lijiang chen, Qi Zhao and Wenquan Feng, ML-FDA: Meta-Learning via Feature Distribution Alignment for Few-Shot Learning[C], IEEE International Conference on Visual Communications and Image Processing, 2022. ( VCIP, oral)
[11] Qi Zhao, Shuchang. Lyu, Yuewen. Li, Yujing. Ma and Lijiang. Chen, MGML: Multigranularity Multilevel Feature Ensemble Network for Remote Sensing Scene Classification[J], IEEE Transactions on Neural Networks and Learning Systems, doi: 10.1109/TNNLS.2021.3106391, 2021. (TNNLS, SCI Q1, IF: 14.255)
[10] Qi Zhao, Yujing Ma, Shuchang Lyu, Lijiang Chen, Embedded Self-Distillation in Compact Multi-Branch Ensemble Network for Remote Sensing Scene Classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2021. (TGRS, SCI Q1, IF:8.125)
[9] Qi Zhao, Shuchang Lyu, Zhiwei Zhang, Ting-Bing Xu, Guangliang Cheng, Embedded Knowledge Distillation in Depth-level Dynamic Neural Network[C], IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2021. (CVPR Workshop, oral, http://sites.google.com/view/cvpr2021-dnetcv)
[8] Xingkui Zhu*, Shuchang Lyu*, Xu Wang, Qi Zhao, TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-captured Scenarios[C]. International Conference on Computer Vision (ICCV) Workshops, 2021. (ICCV Workshop, oral)
[7] Shuchang Lyu, Qi Zhao, Yujing Ma, Lijiang Chen, Make Baseline Model Stronger: Embedded Knowledge Distillation in Weight-Sharing Based Ensemble Network[C]. British Machine Vision Conference, 2021. (BMVC)
[6] Qi Zhao, Jiahui Liu, Yuewen Li, et al. Semantic Segmentation with Attention Mechanism for Remote Sensing Images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2021, pp(99):1-13. (TGRS, SCI Q1, IF:8.125)
[5] Qi Zhao, Nauman Raoof, Shuchang Lyu, et al, RSNet: A Compact Relative Squeezing Net for Image Recognition[C], IEEE International Conference on Visual Communications and Image Processing (VCIP), pp. 1-4, doi: 10.1109/VCIP47243.2019.8966024, 2019. (VCIP, oral presentation)
[4] Qi Zhao, Jiahui Liu, Boxue Zhang, Shuchang Lyu, Interpretable Relative Squeezing Bottleneck Design for Compact convolutional neural networks Model[J], Image and Vision Computing (IVC), 89:276-288, 2019. (IVC, SCI Q2, IF: 3.86)
[3] Qi Zhao, Boxue Zhang, Shuchang Lyu et al., A CNN-SIFT Hybrid Pedestrian Navigation Method based on First-Person Vision[J], Remote Sensing, 10(8), 1229, doi: https://doi-org-443.e2.buaa.edu.cn/10.3390/rs10081229, 2018. (RS, SCI Q1, IF:5.349)
[2] Boxue Zhang, Qi Zhao, Wenquan Feng, Shuchang Lyu, Alpha-MEX: A Smarter Global Pooling Method for Convolutional Neural Networks[J], Neurocomputing, 321:36-48, 2018. (Neurocomputing, SCI Q1, IF: 5.779)
[1] Qi Zhao, Shuchang Lyu, Boxue Zhang, Wenquan Feng, Multi-activation Pooling Method in Convolutional Neural Networks for Image Recognition[J], Wireless Communications and Mobile Computing, Article ID 8196906, 2018. (WCMC, SCI Q3, IF:2.336)
竞赛方面:
2022年参与“2022 航天宏图杯遥感智能影像智能处理算法大赛”,在“国际赛道:遥感影像语义分割”,晋级复赛(top20晋级),最终获得第13名(13/188)。
2021年参与北京市遥感信息研究所和中国科学院人工智能创新研究院联合发布的“天智杯”人工智能挑战赛,在可见光图像建筑智能变化检测赛道,取得第15名的成绩(15/410)
2021年参与ICCV Workshop比赛:“Vision Meets Drones: A Challenge”中的多目标检测赛道,取得总成绩第5名(5/113)。
2020年在商汤科技主办的首届“AI瞰世界,2020人工智能遥感解译大赛”中分获第6名和第10名(6/83,10/83,均获决赛入围奖)
2019年课题组研究生团队获第一届海量光学遥感卫星数据智能处理算法大赛二等奖。
获得主要荣誉
省部级科技进步二等奖一项,排名第六;三等奖一项,排名第二。
社会学术兼职
IEEE通信协会会员,电子学会会员
北京航空航天大学 电子信息工程学院 教师
北京航空航天大学 电子信息工程学院 博士后研究