SPICE: Semantic Pseudo-Labeling for Image Clustering

The similarity among samples and the discrepancy among clusters are two crucial aspects of image clustering. However, current deep clustering methods suffer from inaccurate estimation of either feature similarity or semantic discrepancy. In this paper, we present a Semantic Pseudo-labeling-based Ima...

Full description

Bibliographic Details

Published in:	IEEE transactions on image processing Vol. 31; p. 1
Main Authors:	Niu, Chuang, Shan, Hongming, Wang, Ge
Format:	Journal Article
Language:	English
Published:	United States IEEE 2022 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:	Algorithms Clustering Clustering algorithms Clustering methods Deep clustering Head Labeling Prototypes representation learning self-supervised learning Semantics semi-supervised learning Similarity SPICE Training
ISSN:	1057-7149, 1941-0042, 1941-0042
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!