Deep expectation-maximization network for unsupervised image segmentation and clustering

报告题目： Deep expectation-maximization network for unsupervised image segmentation and clustering

报 告 人：唐年胜 教授 云南大学

报告时间：2023年12月23日（星期六） 17:00-18:00

报告地点：海山楼（创新园大厦）A1101

校内联系人：代国伟 教授    联系电话：84708351-8502

报告摘要：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.

报告人简介：云南大学教授、博士生导师，国家杰出青年科学基金获得者，教育部长江学者特聘教授，国家级教学名师，国家百千万人才工程入选者，获国家“有突出贡献中青年专家”称号，国际统计学会推选会员（ISI Elected Member），国际数理统计学会会士（IMS Fellow），教育部高等学校统计学类专业教学指导委员会委员，第八、九届国家自然科学基金数学天元基金学术领导小组成员。从事生物医学统计、高维数据分析、缺失数据分析、贝叶斯统计、机器学习、变分推断等方面的研究，在JASA、Annals of Statistics、Biometrika等刊物发表学术论文190多篇，出版学术专著5部。《应用回归分析》教材获首届全国优秀教材奖（高等教育类）二等奖。现担任《Statistics and Its Interface》、《Communications in Mathematics and Statistics》等期刊编委或副主编。