Robust Self-Supervised Convolutional Neural Network for Subspace Clustering and Classification
This work addresses limitations in subspace clustering methods for real-world applications, though it appears incremental as it builds upon existing self-supervised approaches.
The paper tackled the problem of subspace clustering and classification by proposing a robust self-supervised convolutional neural network that handles nonlinear manifolds, data corruptions, and out-of-sample data, achieving significant performance improvements over its baseline on four datasets.
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 ($S^2$ConvSCN) 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. $S^2$ConvSCN 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 $S^2$ConvSCN 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.