Logo image
Back
Common and Unique Representation Deep Embedded Clustering
Conference proceeding   Peer reviewed

Common and Unique Representation Deep Embedded Clustering

Don Yates, Hakki Erhan Sevil and Arash Mahyari
2025 IEEE International Conference on Image Processing (ICIP), pp.611-616
IEEE International Conference on Image Processing (ICIP 2025) (Anchorage, Alaska, USA, 09/13/2025–09/16/2025)
08/18/2025
DOI: https://doi.org/10.1109/ICIP55913.2025.11084604

Metrics

13 Record Views

Abstract

A goal of multi-view clustering (MVC) is to discover common features of an object across views while identifying unique features within each view. Deep neural networks are good at feature learning on large-scale unlabeled datasets, but most deep MVC methods struggle to extract and utilize complementary information from view-unique features. Additionally, many lack support for single-sample inference, limiting applications. This paper presents a novel Common and Unique Representation Deep Embedded Clustering (CUR-DEC) architecture and optimization method that learns view-invariant representations, aiding in clustering assignments by leveraging view-unique information. This method is suitable for single-sample inference. We first pretrain an autoencoder to extract both view-common and view-unique features, then a common cluster representation is learned by leveraging complementary information. Experimental results on multi-view datasets show that our method provides significant improvements compared to other deep multi-view clustering methods.

Details

Logo image