A Novel Efficient Approach with Data-Adaptive Capability for OMP-based Sparse Subspace Clustering
This work addresses a specific bottleneck in sparse subspace clustering for data science applications, offering incremental improvements in performance.
The paper tackled the problem of data adaptiveness in Orthogonal Matching Pursuit (OMP)-based sparse subspace clustering by proposing a parameter selection process and a new metric, achieving better clustering accuracy, representation quality, and efficiency compared to existing methods.
Orthogonal Matching Pursuit (OMP) plays an important role in data science and its applications such as sparse subspace clustering and image processing. However, the existing OMP-based approaches lack of data adaptiveness so that the data cannot be represented well enough and may lose the accuracy. This paper proposes a novel approach to enhance the data-adaptive capability for OMP-based sparse subspace clustering. In our method a parameter selection process is developed to adjust the parameters based on the data distribution for information representation. Our theoretical analysis indicates that the parameter selection process can efficiently coordinate with any OMP-based methods to improve the clustering performance. Also a new Self-Expressive-Affinity (SEA) ratio metric is defined to measure the sparse representation conversion efficiency for spectral clustering to obtain data segmentations. Our experiments show that proposed approach can achieve better performances compared with other OMP-based sparse subspace clustering algorithms in terms of clustering accuracy, SEA ratio and representation quality, also keep the time efficiency and anti-noise ability.