Deep Self-representative Concept Factorization Network for Representation Learning

TL;DR

This paper introduces DSCF-Net, a novel deep unsupervised learning framework that enhances feature representation and clustering by discovering hidden semantic features, improving robustness, and preserving local structures.

Contribution

The paper proposes DSCF-Net, integrating deep concept factorization, self-expressive representation, and locality preservation into a unified model for improved unsupervised deep feature learning.

Findings

Achieves state-of-the-art clustering performance on multiple datasets.

Effectively discovers hidden deep semantic features.

Enhances robustness through subspace recovery and noise correction.

Abstract

In this paper, we investigate the unsupervised deep representation learning issue and technically propose a novel framework called Deep Self-representative Concept Factorization Network (DSCF-Net), for clustering deep features. To improve the representation and clustering abilities, DSCF-Net explicitly considers discovering hidden deep semantic features, enhancing the robustness proper-ties of the deep factorization to noise and preserving the local man-ifold structures of deep features. Specifically, DSCF-Net seamlessly integrates the robust deep concept factorization, deep self-expressive representation and adaptive locality preserving feature learning into a unified framework. To discover hidden deep repre-sentations, DSCF-Net designs a hierarchical factorization architec-ture using multiple layers of linear transformations, where the hierarchical representation is performed by formulating the prob-lem as optimizing the basis concepts in each layer to improve the representation indirectly. DSCF-Net also improves the robustness by subspace recovery for sparse error correction firstly and then performs the deep factorization in the recovered visual subspace. To obtain locality-preserving representations, we also present an adaptive deep self-representative weighting strategy by using the coefficient matrix as the adaptive reconstruction weights to keep the locality of representations. Extensive comparison results with several other related models show that DSCF-Net delivers state-of-the-art performance on several public databases.