Is an Affine Constraint Needed for Affine Subspace Clustering?
This addresses a foundational question in subspace clustering for computer vision applications like motion segmentation, clarifying when constraints can be omitted, but it is incremental as it builds on existing theory.
The paper investigates whether an affine constraint is necessary for clustering data from affine subspaces, showing theoretically and empirically that in high-dimensional settings relative to subspace dimensions, the constraint has negligible impact on clustering performance.
Subspace clustering methods based on expressing each data point as a linear combination of other data points have achieved great success in computer vision applications such as motion segmentation, face and digit clustering. In face clustering, the subspaces are linear and subspace clustering methods can be applied directly. In motion segmentation, the subspaces are affine and an additional affine constraint on the coefficients is often enforced. However, since affine subspaces can always be embedded into linear subspaces of one extra dimension, it is unclear if the affine constraint is really necessary. This paper shows, both theoretically and empirically, that when the dimension of the ambient space is high relative to the sum of the dimensions of the affine subspaces, the affine constraint has a negligible effect on clustering performance. Specifically, our analysis provides conditions that guarantee the correctness of affine subspace clustering methods both with and without the affine constraint, and shows that these conditions are satisfied for high-dimensional data. Underlying our analysis is the notion of affinely independent subspaces, which not only provides geometrically interpretable correctness conditions, but also clarifies the relationships between existing results for affine subspace clustering.