Achieving stable subspace clustering by post-processing generic clustering results
This work addresses the issue of clustering stability for researchers in computer vision and machine learning, but it is incremental as it builds upon existing sparse subspace clustering methods.
The paper tackles the problem of improving clustering accuracy in sparse subspace clustering by introducing a post-processing method that reassigns incorrectly clustered points to stable subspaces, resulting in greatly reduced clustering errors on motion segmentation and face clustering datasets.
We propose an effective subspace selection scheme as a post-processing step to improve results obtained by sparse subspace clustering (SSC). Our method starts by the computation of stable subspaces using a novel random sampling scheme. Thus constructed preliminary subspaces are used to identify the initially incorrectly clustered data points and then to reassign them to more suitable clusters based on their goodness-of-fit to the preliminary model. To improve the robustness of the algorithm, we use a dominant nearest subspace classification scheme that controls the level of sensitivity against reassignment. We demonstrate that our algorithm is convergent and superior to the direct application of a generic alternative such as principal component analysis. On several popular datasets for motion segmentation and face clustering pervasively used in the sparse subspace clustering literature the proposed method is shown to reduce greatly the incidence of clustering errors while introducing negligible disturbance to the data points already correctly clustered.