Constructing the F-Graph with a Symmetric Constraint for Subspace Clustering

TL;DR

This paper introduces the F-graph subspace clustering algorithm with a symmetric constraint, which offers a closed-form solution and improves clustering accuracy and efficiency in face and motion segmentation tasks.

Contribution

The paper proposes a novel F-graph subspace clustering method with a symmetric constraint that simplifies computation and enhances performance over existing algorithms.

Findings

Reduces running time significantly

Achieves higher clustering accuracy

Effective in face and motion segmentation

Abstract

Based on further studying the low-rank subspace clustering (LRSC) and L2-graph subspace clustering algorithms, we propose a F-graph subspace clustering algorithm with a symmetric constraint (FSSC), which constructs a new objective function with a symmetric constraint basing on F-norm, whose the most significant advantage is to obtain a closed-form solution of the coefficient matrix. Then, take the absolute value of each element of the coefficient matrix, and retain the k largest coefficients per column, set the other elements to 0, to get a new coefficient matrix. Finally, FSSC performs spectral clustering over the new coefficient matrix. The experimental results on face clustering and motion segmentation show FSSC algorithm can not only obviously reduce the running time, but also achieve higher accuracy compared with the state-of-the-art representation-based subspace clustering algorithms, which verifies that the FSSC algorithm is efficacious and feasible.