Grouping with Bias

This paper considers priors from unitary generative models, partially labeled data and spatial attention, modelled as constraints in the solution space, and demonstrates that simple priors can greatly improve image segmentation results.

Abstract

With the optimization of pattern discrimination as a goal, graph partitioning approaches often lack the capability to integrate prior knowledge to guide grouping. In this paper, we consider priors from unitary generative models, partially labeled data and spatial attention. These priors are modelled as constraints in the solution space. By imposing uniformity condition on the constraints, we restrict the feasible space to one of smooth solutions. A subspace projection method is developed to solve this constrained eigenproblem. We demonstrate that simple priors can greatly improve image segmentation results.