统计与数据科学系系列学术报告之四百一十期

时   间：2023年10月13日（星期五）16:00-17:00

地   点：史带楼604室

题   目：Deep expectation-maximization network for unsupervised image segmentation and clustering

主持人：朱仲义 教授

报告人：唐年胜 教授 云南大学数学与统计学院

报告人简介：唐年胜，博士，国家杰出青年科学基金获得者，教育部“**学者”特聘教授，教育部“新世纪优秀人才”，云南省科技领军人才，云南省首批云岭学者，云南省中青年学术和技术带头人，云南省教学名师，云南省学位委员会经济与管理学科评议组成员，博士生导师。 云南省高校“统计与信息技术重点实验室 ” 负责人，“云南大学复杂数据统计推断方法研究 ” 省创新团队带头人。

摘   要：Unsupervised learning, such as unsupervised image segmentation and clustering, are fundamentaltasks in image representation learning. In this paper, we design a deep expectation-maximization (DEM) network for unsupervised image segmentation and clustering. Itis based on the statistical modeling of image in its latentfeature space by Gaussian mixture model (GMM), implemented in a novel deep learning framework. Specifically, in the unsupervised setting, we design an auto-encoder network and an EM module over the image latent features, for jointly learning the image latent features and GMM model of the latent features in a single framework. To construct the EM-module, we unfold the iterative operations of EM algorithm and the online EM algorithm in fixed steps to be differentiable network blocks, plugged into the network to estimate the GMM parameters of the image latent features. The proposed network parameters can be end-to-end optimized using losses based on log-likelihood of GMM, entropy of Gaussian component assignment probabilities and image reconstruction error. Extensive experiments confirm that our proposed networks achieve favorable results compared with several state-of-the-art methods in unsupervised image segmentation and clustering.

统计与数据科学系

2023-10-8