报告题目：Robust Al-aided Imaging Models without Labeled Samples

报告人：包承龙

单   位：清华大学

时   间： 6月8日15:10-16:10

地   点：河南大学龙子湖校区九章学堂C座302（ZOOMID： 567-306-5241 密码：123456）

摘 要：The observations in practical imaging systems always contain complex noise such that classic approaches are difficult to obtain satisfactory results. In recent years, deep neural networks directly learned a map between the noisy and clean images based on the training on paired data. Despite its promising results in various tasks, collecting the training data is difficult and time-consuming in practice. In this talk, in the unpaired data regime, we will discuss our recent progress for building AI-aided robust models and their applications in image processing. Leveraging the Bayesian inference framework our model combines classical mathematical and deep neural networks improve interpretability. Experimental results on various datasets validate the advantages of the proposed methods. Finally, I will report the recent progresses on solving the preferred orientation problems in cyroEM using the developed tools.

报告人简介：The observations in practical imaging systems always contain complex noise such that classic approaches are difficult to obtain satisfactory results. Chenglong Bao is currently an assistant professor in Yau mathematical sciences center at Tsinghua university. He obtained the Ph.D. in Mathematics from National of Singapore University in 2014. His research interests include computational models and algorithms for solving imaging problems, and has published over 40 papers in top venues.邀请人: 庞志峰