基于双分支小波卷积自编码器和数据增强的深度聚类方法  

Deep Clustering Method Based on Dual-branch Wavelet Convolutional Autoencoder and Data Augmentation

作　　者：安瑞 鲁进[1,2] 杨晶晶 AN Rui;LU Jin;YANG Jingjing(School of Information Science and Engineering,Yunnan University,Kunming 650504,China;Key Laboratory of Internet of Things Technology and Applications in Higher Education Institutions of Yunnan Province,Kunming 650504,China)

机构地区：[1]云南大学信息学院,昆明650504 [2]云南省高校物联网技术及应用重点实验室,昆明650504

出　　处：《计算机科学》2025年第4期129-137,共9页Computer Science

基　　金：国家自然科学基金(62261059,61966037);云南省基础研究专项重点项目(202301AS070025)。

摘　　要：基于自编码器的深度聚类是无监督学习的代表算法,近年来在计算机视觉领域获得了诸多关注。相较于传统算法,自动编码器隐藏层紧凑的表示空间为聚类任务提供了更为灵活的条件。现有的自编码器聚类大多使用单分支编码器网络,而采用多个网络结合的双编码器结构还有较大的探索空间。为此,提出了一种基于双分支小波卷积自编码器和数据增强的深度聚类方法DB-WCAE-DA(Deep Clustering Method Based on Dual-Branch Wavelet Convolutional Autoencoder and Data Augmentation)。首先,融合小波变换设计了一种双分支的卷积自编码器结构,将数据映射到低维特征空间进行聚类。其次,在一个分支上采用VMF混合模型构建聚类软分配,保留数据的几何结构和方向信息;在另一个分支上引入数据增强技术,并在嵌入空间中添加噪声,提高编码器对特征的学习能力。通过这种双分支嵌套式优化过程不断提炼数据特征,使得聚类结果更加可靠。最后,在多个基准数据集上验证了该模型的有效性。Deep clustering based on autoencoders is a representative algorithm for unsupervised learning.It has gained much attention in the field of computer vision in recent years.Compared to traditional algorithms,the compact representation space provided by the hidden layers of autoencoders offers a more flexible condition for clustering tasks.Existing autoencoder clustering methods mostly use a single-branch encoder network,while the exploration space for a dual-encoder structure combining multiple networks is still significant.To address this,a deep clustering method named DB-WCAE-DA(Deep Clustering Method Based on Dual-branch Wavelet Convolutional Autoencoder and Data Augmentation)is proposed.Firstly,a dual-branch convolutional autoencoder structure is designed by integrating wavelet transformation,mapping the data to a low-dimensional feature space for clustering.Secondly,on one branch,a von mises-fisher(VMF)mixture model is employed to construct a soft clustering assignment,preserving the geometric structure and directional information of the data.On the other branch,data augmentation techniques are introduced,along with the addition of noise in the embedded space,to enhance the encoder’s learning capabilities.Through this dual-branch nested optimization process,the features of the data are continuously refined,resulting in more reliable clustering outcomes.Finally,the effectiveness of the model is validated on multiple benchmark datasets.

关 键 词：无监督学习 深度聚类 数据增强 小波变换 双分支自编码器 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]