20161018-35 Sifei Liu: Learning Recursive Filters for...

报告嘉宾2：Sifei Liu (UC Merced, CA, US)

报告时间：2016年10月18日（星期二）晚21:00（北京时间）

报告题目：Learning Recursive Filters for Low-Level Vision via a Hybrid Neural Network 

主持人： 吴毅（南京信息工程大学）

报告摘要：

In this paper, we consider numerous low-level vision problems (e.g., edge-preserving filtering and denoising) as recursive image filtering via a hybrid neural network. The network contains several spatially variant recurrent neural networks (RNN) as equivalents of a group of distinct recursive filters for each pixel, and a deep convolutional neural network (CNN) that learns the weights of RNNs. The deep CNN can learn regulations of recurrent propagation for various tasks and effectively guides recurrent propagation over an entire image. The proposed model does not need a large number of convolutional channels nor big kernels to learn features for low-level vision filters. It is significantly smaller and faster in comparison with a deep CNN based image filter. Experimental results show that many low-level vision tasks can be effectively learned and carried out in real-time by the proposed algorithm.

参考文献：

Paper title, authors, Journal, 2015

[1] Sifei Liu, Jinshan Pan, Ming-Hsuan Yang, Learning Recursive Filters for Low-Level Vision via a Hybrid Neural Network. ECCV 2016 (Oral).

报告人简介：

Sifei Liu is a Ph.D candidate in computer science at University of California, Merced, department of EECS under Prof. Ming-Hsuan Yang. Her research interests are in computer vision and machine learning. She completed the M.C.S. at University of Science and Technology of China (USTC) under Stan.Z Li and Bin Li, and received the B.S. in control science and technology from North China Electric Power University. She did several interns at Baidu IDL, Beijing, MMlab Hongkong, and won the Baidu fellowship at the summer of 2013.

特别鸣谢本次Webinar主要组织者：

VOOC责任委员：何晖光（中国科学院自动化研究所）

VODB协调理事：张利军（南京大学），章国锋（浙江大学）

[Slides]