Higher-order Segmentation via Multicuts
This work addresses segmentation challenges in image analysis and computer vision, presenting incremental improvements through dedicated algorithms and relaxations.
The paper tackled the problem of image segmentation using higher-order models by developing a systematic computational inference method for multicuts, achieving globally optimal evaluation for a significant subset of models without runtime compromise.
Multicuts enable to conveniently represent discrete graphical models for unsupervised and supervised image segmentation, in the case of local energy functions that exhibit symmetries. The basic Potts model and natural extensions thereof to higher-order models provide a prominent class of such objectives, that cover a broad range of segmentation problems relevant to image analysis and computer vision. We exhibit a way to systematically take into account such higher-order terms for computational inference. Furthermore, we present results of a comprehensive and competitive numerical evaluation of a variety of dedicated cutting-plane algorithms. Our approach enables the globally optimal evaluation of a significant subset of these models, without compromising runtime. Polynomially solvable relaxations are studied as well, along with advanced rounding schemes for post-processing.