Regularized neural networks and convex shape priori for image segmentation

发布者：季洁发布时间：2019-11-04浏览次数：191

Speaker:Xue-Cheng Tai (Hong Kong Baptist University)
Host:Ke Wei, School of Data Science, Fudan University
Time:4:00-5:00 pm, Nov 4, 2019
Location:Zibin N102, Fudan University
Abstract:I will present some new research work in several directions. The first part is devoted to study of deep neural networks. We propose some special techniques to add spatial regularization effects to popular deep neural networks. We use numerical experiments to show that the regularized DNN always has smooth boundary when used for image segmentation and similar classification problems. We want to emphasis that our spatial regularization effect is naturally integrated into existing deep neural networks and it only require minimal algorithmic modifications to existing neural networks. It offers very effective stability and smoothing effects into commonly used neural networks. In the last part, we will briefly mention some of recent research on convex shape representation for medical applications.
Bio:台雪成，香港浸会大学教授，挪威卑尔根大学数学系终身教授，曾担任挪威奥斯陆大学国家应用数学中心和挪威综合石油研究中心CIPR兼职教授，计算数学与科学工程计算、图像处理与分析领域国际知名学者。因其在科学计算方面的突出成就，曾获得第八届冯康科学计算奖和新加波南洋科研卓越成就奖。台教授研究领域主要包括偏微分方程的数值方法、优化技术、计算机视觉以及图像处理等，是SIAM J. Image Scienc., J. Mathematical Imaging and Vision, Inverse problems and imaging 等多个国际知名期刊的编委成员， 在SIAM J. Imaging Science，SIAM J. Sci. Comput.，IEEE Trans. on Image Processing，SIAM J. Numer. Anal. 等国际顶级杂志和CVPR、ECCV等国际顶级会议上共发表多篇高质量的论文。担任多个国际会议的特邀报告人，组委和大会主席。