English

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

Computer Vision and Pattern Recognition 2020-04-08 v1 Machine Learning Machine Learning

Abstract

Insufficient capability of existing subspace clustering methods to handle data coming from nonlinear manifolds, data corruptions, and out-of-sample data hinders their applicability to address real-world clustering and classification problems. This paper proposes the robust formulation of the self-supervised convolutional subspace clustering network (S2S^2ConvSCN) that incorporates the fully connected (FC) layer and, thus, it is capable for handling out-of-sample data by classifying them using a softmax classifier. S2S^2ConvSCN clusters data coming from nonlinear manifolds by learning the linear self-representation model in the feature space. Robustness to data corruptions is achieved by using the correntropy induced metric (CIM) of the error. Furthermore, the block-diagonal (BD) structure of the representation matrix is enforced explicitly through BD regularization. In a truly unsupervised training environment, Robust S2S^2ConvSCN outperforms its baseline version by a significant amount for both seen and unseen data on four well-known datasets. Arguably, such an ablation study has not been reported before.

Keywords

Cite

@article{arxiv.2004.03375,
  title  = {Robust Self-Supervised Convolutional Neural Network for Subspace Clustering and Classification},
  author = {Dario Sitnik and Ivica Kopriva},
  journal= {arXiv preprint arXiv:2004.03375},
  year   = {2020}
}

Comments

15 pages, 3 tables, 3 figures

R2 v1 2026-06-23T14:42:49.099Z