.png){kind=icon}
.png){kind=icon}
Return
Adaptive Correlation Integration for Deep Image Clustering
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2022.06.059.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Deep clustering methods often estimate data correlations to guide unsupervised learning. However, since different kinds of correlations capture different data characteristics, a strong data correlation may not be appropriate for every case. In this paper, we propose a novel Teacher-Student framework to adaptively estimate correlation and interactively learn a deep clustering model for various data distributions. Specifically, a teacher module mines and integrates various kinds of correlations from different perspectives. To adapt to various cases, we propose a novel Adaptive Integration Gate (ADI-Gate) to selectively and dynamically integrate different data correlations in a teaching-feedback manner. Furthermore, a student module performs unsupervised clustering inference with the estimated correlation and provides a preference for teacher module. We also design a Pairwise-Weighted loss (PW-loss) to enhance high confident correlation guidance of data pairs during the learning process of student module. In image clustering experiments on four public datasets, our model achieves consistent improvements over state-ofthe-art models.(c) 2022 Published by Elsevier B.V.
Keywords:
Deep Image Clustering
Teacher-Student Framework
Cluster Ensemble