报告人：唐年胜
报告地点：腾讯会议ID:966713519
报告时间：2023年11月20日星期一16:30-17:30
邀请人：高巍
报告摘要：
Unsupervised learning, such as unsupervised image segmentation and clustering, are fundamental tasks 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 latent feature 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.
主讲人简介：
唐年胜，云南大学数学与统计学院二级教授，博士生导师，院长。“国家杰出青年科学基金”获得者，教育部“长江学者特聘教授”，教育部“新世纪优秀人才支持计划”入选者，国家百千万人才工程暨有突出贡献中青年专家，享受国务院政府特殊津贴。国际统计学会推选会员，国际数理统计学会会士（IMS Fellow）。曾获霍英东教育基金会第九届高等院校青年教师奖，云南省自然科学一等奖1项、二等奖2项、三等奖1项，国家统计局全国统计科研优秀成果二等奖6项；国际泛华统计协会Outstanding Service Award。在Journal of the American Statistical Association（美国统计学会会刊）、Annals of Statistics、Biomertrika等学术期刊发表论文170余篇，出版专著4部。
