Detailed Information

Cited 0 time in webofscience Cited 0 time in scopus
Metadata Downloads

Deep Clustering for Improved Inter-Cluster Separability and Intra-Cluster Homogeneity with Cohesive Loss

Authors
Kim, ByeonghakLoew, MurrayHan, David K.Ko, Hanseok
Issue Date
5월-2021
Publisher
IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG
Keywords
separate clustering; convolutional autoencoder; intra-cluster homogeneity; inter-cluster separability
Citation
IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, v.E104D, no.5, pp.776 - 780
Indexed
SCIE
SCOPUS
Journal Title
IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS
Volume
E104D
Number
5
Start Page
776
End Page
780
URI
https://scholar.korea.ac.kr/handle/2021.sw.korea/128116
DOI
10.1587/transinf.2020EDL8138
ISSN
0916-8532
Abstract
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.
Files in This Item
There are no files associated with this item.
Appears in
Collections
College of Engineering > School of Electrical Engineering > 1. Journal Articles

qrcode

Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Researcher Ko, Han seok photo

Ko, Han seok
공과대학 (전기전자공학부)
Read more

Altmetrics

Total Views & Downloads

BROWSE