English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Insufficient capability of existing subspace clustering methods to handledata coming from nonlinear manifolds, data corruptions, and out-of-sample datahinders their applicability to address real-world clustering and classificationproblems. This paper proposes the robust formulation of the self-supervisedconvolutional subspace clustering network ($S^2$ConvSCN) that incorporates thefully connected (FC) layer and, thus, it is capable for handling out-of-sampledata by classifying them using a softmax classifier. $S^2$ConvSCN clusters datacoming from nonlinear manifolds by learning the linear self-representationmodel in the feature space. Robustness to data corruptions is achieved by usingthe correntropy induced metric (CIM) of the error. Furthermore, theblock-diagonal (BD) structure of the representation matrix is enforcedexplicitly through BD regularization. In a truly unsupervised trainingenvironment, Robust $S^2$ConvSCN outperforms its baseline version by asignificant amount for both seen and unseen data on four well-known datasets.Arguably, such an ablation study has not been reported before.

Robust Self-Supervised Convolutional Neural Network for Subspace Clustering and Classification