Efficient Pose and Cell Segmentation using Column Generation
This work addresses segmentation challenges in computer vision and bioimaging, presenting an incremental improvement with a generic relaxation method.
The authors tackled multi-person pose segmentation in natural images and instance segmentation in crowded biological cells by formulating them as integer programs and using a column generation relaxation scheme for efficient optimization.
We study the problems of multi-person pose segmentation in natural images and instance segmentation in biological images with crowded cells. We formulate these distinct tasks as integer programs where variables correspond to poses/cells. To optimize, we propose a generic relaxation scheme for solving these combinatorial problems using a column generation formulation where the program for generating a column is solved via exact optimization of very small scale integer programs. This results in efficient exploration of the spaces of poses and cells.