Extra Proximal-Gradient Inspired Non-local Network

Published:2019-06-02 

Title:         Extra Proximal-Gradient Inspired Non-local Network
Time:     10:00-11:00, June5  Monday,2019
Location:   Room 1002, Science Building B
Lecturer: Prof.Yunmei CHEN   University of Florida, USA

 

Abstract:
Variational method and deep learning method are two mainstream powerful approaches to solve inverse problems in computer vision.  To take advantages of advanced optimization algorithms and powerful representation ability of deep neural networks, we propose a novel deep network for image reconstruction and restoration.  The architecture of this network is inspired by our proposed accelerated extra proximal gradient algorithm. It is able to incorporate non-local operation to  xploit the non-local self-similarity of the images and to learn the  nonlinear transform, under which the solution is sparse. Our experimental results showed that our network outperforms several state-of-the-art deep networks with similar number or only slightly increased number of learnable parameter.

School of Software Engineering
www.sei.ecnu.edu.cn Copyright Software Engineering Institute
E-mail:yuanzhang@sei.ecnu.edu.cn | Tel:021-62232550 | Address:Zhongshan North Road 3663, Shanghai