Discrete-Continuous ADMM for Transductive Inference in Higher-Order MRFs
This addresses the problem of efficient and accurate segmentation for computer vision researchers, offering a novel optimization approach that is incremental over prior convex relaxations.
The paper tackles transductive inference in higher-order MRFs by jointly optimizing continuous classifier parameters and discrete label variables, proposing a decoupling into discrete and continuous subproblems with an ADMM-related method that preserves integrality and guarantees global convergence. It demonstrates advantages in experiments such as video object segmentation on DAVIS and interactive image segmentation.
This paper introduces a novel algorithm for transductive inference in higher-order MRFs, where the unary energies are parameterized by a variable classifier. The considered task is posed as a joint optimization problem in the continuous classifier parameters and the discrete label variables. In contrast to prior approaches such as convex relaxations, we propose an advantageous decoupling of the objective function into discrete and continuous subproblems and a novel, efficient optimization method related to ADMM. This approach preserves integrality of the discrete label variables and guarantees global convergence to a critical point. We demonstrate the advantages of our approach in several experiments including video object segmentation on the DAVIS data set and interactive image segmentation.