Deep clustering for improved inter-cluster separability and intra-cluster homogeneity with cohesive loss

Byeonghak Kim, Murray Loew, David K. Han, Hanseok Ko

Research output: Contribution to journalArticlepeer-review


To date, many studies have employed clustering for the classification of unlabeled data. Deep separate clustering applies several deep learning models to conventional clustering algorithms to more clearly separate the distribution of the clusters. In this paper, we employ a convolutional autoencoder to learn the features of input images. Following this, k-means clustering is conducted using the encoded layer features learned by the convolutional autoencoder. A center loss function is then added to aggregate the data points into clusters to increase the intra-cluster homogeneity. Finally, we calculate and increase the inter-cluster separability. We combine all loss functions into a single global objective function. Our new deep clustering method surpasses the performance of existing clustering approaches when compared in experiments under the same conditions.

Original languageEnglish
Pages (from-to)776-780
Number of pages5
JournalIEICE Transactions on Information and Systems
Issue number5
Publication statusPublished - 2021

Bibliographical note

Funding Information:
Fund project for infectious disease research (GFID), Republic of Korea (grant number: HG19C0682). The work of Murray Loew was supported by GWU (KU-GWU Joint Research Fund).

Funding Information:
This research was supported by Government-wide R&D

Publisher Copyright:
Copyright © 2021 The Institute of Electronics, Information and Communication Engineers


  • Convolutional autoencoder
  • Inter-cluster separability
  • Intra-cluster homogeneity
  • Separate clustering

ASJC Scopus subject areas

  • Software
  • Hardware and Architecture
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering
  • Artificial Intelligence


Dive into the research topics of 'Deep clustering for improved inter-cluster separability and intra-cluster homogeneity with cohesive loss'. Together they form a unique fingerprint.

Cite this