清华主页 EN
导航菜单

Deep image prior for inverse problems: acceleration and probabilistic treatment

来源: 11-21

时间:Mon., 14:00-15:00, Nov.21th, 2022

地点:Tencent Meeting ID: 431642438

主讲人:Bangti Jin 金邦梯 The Chinese University of Hong Kong

Abstract

Since its first proposal in 2018, deep image prior has emerged as a very powerful unsupervised deep learning technique for solving inverse problems. The approach has demonstrated very encouraging empirical success in image denoising, deblurring, super-resolution etc. However, there are also several known drawbacks of the approach, notably high computational expense. In this talk, we describe some of our efforts: we propose to accelerate the training process by pretraining on synthetic dataset and further we propose a novel probabilistic treatment of deep image prior to facilitate uncertainty quantification.


Speaker

Bangti Jin's research interests include inverse problems, numerical analysis and machine learning. Currently he serves on the editorial board of five journals, including Inverse Problems and Journal of Computational Mathematics.

https://www.math.cuhk.edu.hk/~btjin/


返回顶部
相关文章
  • Topics in Inverse Problems

    Note: Due to the COVID-19,the course will be delivered online from May 9. 课程描述 DescriptionInverse problem refers to a kind of problem of inverting the physical parameters and geometric features of the interested area by the measured data, and is an important subject for the intersection of industrial and applied mathematics. It consists of many areas including modeling, partial differenti...

  • Deep Generative Models

    Description: This course introduces how to develop deep generative models (DGMs) by integrating probabilistic graphical models and deep learning to generate realistic data including images, texts, graphs, etc. Course contents include 1) basics of probabilistic graphical models, including Bayesian network and Markov random field; 2) posterior inference methods, including message passing, variat...