Deep self-representative subspace clustering network. (October 2021)

• Record Type: Journal Article
• Authors: Baek, Sangwon; Yoon, Gangjoon; Song, Jinjoo; Yoon, Sang Min
• Is Part Of: Pattern recognition. Volume 118(2021)
• Publication Date: 2021-10
• Subjects: Subspace clustering -- Self-representation -- Deep subspace clustering; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2021.108041
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: Deep subspace clustering using self-representative network is proposed. Feature extraction and emphasis network using attention model is introduced. Dimensional reduction in self-expressive layer is presented. We experimentally verify performance improvements for the proposed approach. Abstract: Deep learning based subspace clustering networks have been a significant technique for motion segmentation, unsupervised image segmentation, image representation and compression, and face clustering by separating the high-dimensional data points into their representative low-dimensional linear subspaces. Effective feature selection is critical to remove redundant samples and select the representative feature subset from high-dimensional data space; hence deriving the number of subspaces, their dimensions, data segmentation, and a basis for each subspace. The effective self-representative feature selection and emphasis by scaling the feature map in the learned embedded space is required for deep learning based subspace clustering to reduce the number of parameters and dimension of the self-representative layer. In this paper, we propose a self-representative feature extraction deep neural network for unsupervised subspace clustering to improve representativeness and clustering ability. The extensive relevant results on various data demonstrate that deep subspace clustering employing self-representative features from high-dimensional data can effectively reduce the dimension of the self-representative layer while improving performance.