公共目录

您目前的位置: 首页» 公共目录» 学术活动

学术报告:Quantization of Fully Convolutional Networks for Accurate Biomedical Image Segmentation

题:  Quantization of Fully Convolutional Networks for Accurate Biomedical Image Segmentation

  人:史弋宇 博士(美国圣母大学)
 间:20181026日下午15:30

 点:信息工程学院二层小会议室

   位: 首都师范大学信息工程学院

主讲学者简介:

Dr. Yiyu Shi is currently an associate professor in the Department of Computer Science and Engineering at the University of Notre Dame, and the site director of National Science Foundation (NSF) I/UCRC Alternative and Sustainable Computing. He received his B.S. degree (with honor) from Tsinghua University, Beijing, China in 2005, the M.S and Ph.D. degree from the University of California, Los Angeles in 2007 and 2009 respectively. His current research interests include hardware intelligence with focus on biomedical applications. In recognition of his research, many of his papers have been nominated for the Best Paper Awards in top conferences. He was also the recipient of August-Wilhelm Scheer visiting professorship at Technical University of Munich, IBM Invention Achievement Award, Japan Society for the Promotion of Science (JSPS) Faculty Invitation Fellowship, Humboldt Research Fellowship, IEEE St. Louis Section Outstanding Educator Award, Academy of Science (St. Louis) Innovation Award, Missouri S&T Faculty Excellence Award, NSF CAREER Award, IEEE Region 5 Outstanding Individual Achievement Award, and the Air Force Summer Faculty Fellowship. He has served on the technical program committee of many international conferences including DAC, ICCAD, DATE, ISPD, ASPDAC and ICCD. He is an executive committee member of ACM SIGDA, a member of IEEE CEDA Publicity Committee, deputy editor-in-chief of IEEE VLSI CAS Newsletter, and an associate editor of IEEE TCAD, ACM JETC, VLSI Integration, and IEEE TCCCPS Newsletter.

 

内容介绍:

Biomedical image segmentation plays a central role in quantitative analysis, clinical diagnosis, and medical intervention. Since manual annotation suffers from limited reproducibility, arduous efforts, and excessive time, automatic segmentation is desired to process increasingly larger scale histopathological data. Towards this, deep neural networks (DNNs), particularly fully convolutional networks (FCNs), have been widely adopted. At the same time, quantization of DNNs has become an active research topic, which aims to represent weights with less memory (precision) to considerably reduce memory and computation requirements of DNNs with certain accuracy loss. In this talk, we will show that interestingly, quantization can be used as a method to reduce over-fitting in FCNs for better biomedical image segmentation accuracy. Extensive experiments on the MICCAI Gland dataset show that our method exceeds the current state-of-the-art performance by up to 1%.