讲座题目：Extra Proximal-Gradient Inspired Non-local Network for Image Reconstruction
主讲人：陈韵梅教授 佛罗里达大学
讲座时间：2019年5月27日（周一）上午10：00-11:30
讲座地点：综合楼601
主讲人简介：陈韵梅教授是美国佛罗里达大学终身教授、杰出教授，图像处理科学家，致力于数学、图像处理和机器学习等交叉学科的研究。研究领域涉及医学图像分析中数学模型的建立与数值优化方法的发展，并对其中潜在的数学理论进行了深入的研究。陈韵梅教授在国际上具有崇高的学术地位，被公认为偏微分方程与图像处理领域内的世界级科学家，曾获中华人民共和国国家自然科学三等奖、中华人民共和国教育部科技进步一等奖，获国际发明专利9项，主持美国国家级项目20余项，发表学术论文200余篇。
讲座摘要：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 representational ability of deep neural networks, we propose a novel deep convolutional  neural network for image reconstruction.  The architecture of this network is inspired by our proposed accelerated extra proximal gradient algorithm with the incorporation of two types of prior-exploiting operations.  They are a non-local operation to exploit the inherent non-local self-similarity of the images, and a sparsity-promoting operation to learn the nonlinear transform, under which the solution is sparse. Our experimental results showed that the proposed CNN outperforms several state-of-the-art deep neural networks with similar or even less number of learnable parameters.