文献类型：期刊文献

英文题名：Deep adaptive fuzzy clustering for evolutionary unsupervised representation learning

作者：Tan, Dayu[1,2]; Huang, Zheng[2]; Peng, Xin[1]; Zhong, Weimin[1,3]; Mahalec, Vladimir[2,4]

机构：[1] Key Laboratory of Advanced Control and Optimization for Chemical Processes, Ministry of Education, East China University of Science and Technology, Shanghai, 200237, China; [2] School of Engineering Practice and Technology, McMaster University, Hamilton, ON, L8S 4L7, Canada; [3] Shanghai Institute of Intelligent Science and Technology, Tongji University, Shanghai, 200092, China; [4] Department of Chemical Engineering, McMaster University, Hamilton, ON, L8S 4L7, Canada

年份：2021

外文期刊名：arXiv

收录：EI(收录号：20210097969)

语种：英文

外文关键词：Cluster analysis - Convolutional neural networks - Deep neural networks - Fuzzy inference - Fuzzy neural networks - Iterative methods - Quality control - Unsupervised learning

摘要：Cluster assignment of large and complex images is a crucial but challenging task in pattern recognition and computer vision. In this study, we explore the possibility of employing fuzzy clustering in a deep neural network framework. Thus, we present a novel evolutionary unsupervised learning representation model with iterative optimization. It implements the deep adaptive fuzzy clustering (DAFC) strategy that learns a convolutional neural network classifier from given only unlabeled data samples. DAFC consists of a deep feature quality-verifying model and a fuzzy clustering model, where deep feature representation learning loss function and embedded fuzzy clustering with the weighted adaptive entropy is implemented. We joint fuzzy clustering to the deep reconstruction model, in which fuzzy membership is utilized to represent a clear structure of deep cluster assignments and jointly optimize for the deep representation learning and clustering. Also, the joint model evaluates current clustering performance by inspecting whether the re-sampled data from estimated bottleneck space have consistent clustering properties to progressively improve the deep clustering model. Comprehensive experiments on a variety of datasets show that the proposed method obtains a substantially better performance for both reconstruction and clustering quality when compared to the other state-of-the-art deep clustering methods, as demonstrated with the in-depth analysis in the extensive experiments. Copyright ? 2021, The Authors. All rights reserved.