报告人：吴春林教授

报告题目：An image decompostion induced deep unfolding network for spare feature segmentation

报告摘要：

(1) In this talk, I will present a very recent work, a sparse feature segmentation network for tasks where the target objects are sparsely distributed and the background is hard to be mathematically modeled. We start from an image decomposition model with sparsity regularization, and propose a deep unfolding network, namely IDNet, based on an iterative solver, scaled alternating direction method of multipliers (scaled-ADMM). The IDNet splits raw inputs into double feature layers. Then a new task-oriented segmentation network is constructed, dubbed as IDmUNet, based on the proposed IDNets and a mini-UNet.

(2) This IDmUNet combines the advantages of mathematical modeling and datadriven approaches. Firstly, our approach has mathematical interpretability and can achieve favorable performance with far fewer learnable parameters. Secondly, our IDmUNet is robust in a simple end-to-end training with explainable behaviors. In the experiments of retinal vessel segmentation (RVS), IDmUNet produces the state-of-the-art results with only 0.07m parameters, whereas SA-UNet, one of the latest variants of UNet, contains 0.54m and the original UNet 31.04m.Moreover, the training procedure of our network converges faster without overfitting phenomenon. The paper is now posted on arXiv.org.

报告时间：2022.12.7   下午16:00-19:00

报告形式：腾讯会议；  会议号：777-929-541

获取会议密码请发邮件至：mathywj@hit.edu.cn

报告人简介：吴春林，南开大学数学科学学院教授。吴博士分别于2001年和2006年在中国科学技术大学获得学士和博士学位。曾在中国科学技术大学，新加坡南洋理工大学，新加坡国立大学从事博士后研究工作。他的研究兴趣包括图像与几何计算，数值逼近与优化。近年来吴博士在国际图像科学及计算数学知名杂志如Appl. Comput. Harm. Anal., SIAM J. Numerical Analysis, SIAM J. Scientific Computing, SIAM J. Imaging Sciences, Inverse Problems, J. Sci. Comput., ACM TOG, IEEE TVCG, IEEE TIP, IEEE TMI等上发表多篇学术论文，并主持多项国家自然科学基金。