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[3];Peng, Xin[2];Zhong, Weimin[2];Mahalec, Vladimir[3]

机构：[1]Anhui Univ, Inst Phys Sci & Informat Technol, Key Lab Intelligent Comp & Signal Proc, Minist Educ, Hefei 230601, Peoples R China;[2]East China Univ Sci & Technol, Key Lab Smart Mfg Energy Chem Proc, Minist Educ, Shanghai 200237, Peoples R China;[3]McMaster Univ, Sch Engn Practice & Technol, Hamilton, ON L8S 4L7, Canada

年份：2024

卷号：35

期号：5

起止页码：6103

外文期刊名：IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS

收录：;EI(收录号：20231013684839);WOS:【SCI-EXPANDED(收录号:WOS:000936279600001)】；

基金：This work was supported in part by the National Natural Science Foundation of China (BasicScience Center Program) under Grant 61988101, in part by the National Natural Science Fund for Distinguished Young Scholars under Grant 61925305, in part by the Shanghai Rising-Star Program under Grant 22QA1402400, in part by the National Natural Science Foundation of China 62173145, and in part by the Fundamental Research Funds for the Central Universities and ShanghaiAI Lab.

语种：英文

外文关键词：Representation learning; Feature extraction; Training; Clustering methods; Adaptation models; Neural networks; Image reconstruction; Adaptive loss; ConvNets; deep clustering; feature extraction (FE); fuzzy membership; representation learning

摘要：Cluster assignment of large and complex datasets 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 resampled data from estimated bottleneck space have consistent clustering properties to improve the deep clustering model progressively. Experiments on various datasets show that the proposed method obtains a substantially better performance for both reconstruction and clustering quality compared to the other state-of-the-art deep clustering methods, as demonstrated with the in-depth analysis in the extensive experiments.