Back to Search
Start Over
Adaptive Correlation Integration for Deep Image Clustering.
- Source :
-
Neurocomputing . Aug2022, Vol. 501, p650-663. 14p. - Publication Year :
- 2022
-
Abstract
- 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 Ad aptive I ntegration 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-of-the-art models. [ABSTRACT FROM AUTHOR]
- Subjects :
- *LEARNING
*DATA distribution
*DEEP learning
Subjects
Details
- Language :
- English
- ISSN :
- 09252312
- Volume :
- 501
- Database :
- Academic Search Index
- Journal :
- Neurocomputing
- Publication Type :
- Academic Journal
- Accession number :
- 157909867
- Full Text :
- https://doi.org/10.1016/j.neucom.2022.06.059