Conference item icon

Conference item

Selective pseudo-label clustering

Abstract:

Deep neural networks (DNNs) offer a means of addressing the challenging task of clustering high-dimensional data. DNNs can extract useful features, and so produce a lower dimensional representation, which is more amenable to clustering techniques. As clustering is typically performed in a purely unsupervised setting, where no training labels are available, the question then arises as to how the DNN feature extractor can be trained. The most accurate existing approaches combine the training of...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed

Actions


Access Document


Authors


Contributors

Role:
Editor
Role:
Editor
Role:
Editor
Publisher:
Springer
Host title:
KI 2021: Advances in Artificial Intelligence. KI 2021
Series:
Lecture Notes in Artificial Intelligence
Volume:
12873
Pages:
158-178
Publication date:
2021-09-30
Acceptance date:
2021-06-29
Event title:
44th German Conference on Artificial Intelligence
Event location:
Berlin, Germany & Virtual
Event website:
https://ki2021.uni-luebeck.de/
Event start date:
2021-09-27
Event end date:
2021-10-01
DOI:
ISSN:
0302-9743
EISBN:
978-3-030-87626-5
ISBN:
978-3-030-87625-8
Language:
English
Keywords:
Pubs id:
1187430
Local pid:
pubs:1187430
Deposit date:
2021-07-24

Terms of use


Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP