Tree-Cut for Probabilistic Image Segmentation
This work addresses the problem of multiscale image segmentation for computer vision researchers, offering a probabilistic approach that generalizes beyond single-scale evaluations, though it is incremental in building on existing tree-based representations.
The paper tackles image segmentation by introducing a probabilistic generative model that samples segmentations at specific scales from a region tree, achieving results comparable to the leading gPb-owt-ucm method while producing a distribution over all possible tree-consistent segmentations.
This paper presents a new probabilistic generative model for image segmentation, i.e. the task of partitioning an image into homogeneous regions. Our model is grounded on a mid-level image representation, called a region tree, in which regions are recursively split into subregions until superpixels are reached. Given the region tree, image segmentation is formalized as sampling cuts in the tree from the model. Inference for the cuts is exact, and formulated using dynamic programming. Our tree-cut model can be tuned to sample segmentations at a particular scale of interest out of many possible multiscale image segmentations. This generalizes the common notion that there should be only one correct segmentation per image. Also, it allows moving beyond the standard single-scale evaluation, where the segmentation result for an image is averaged against the corresponding set of coarse and fine human annotations, to conduct a scale-specific evaluation. Our quantitative results are comparable to those of the leading gPb-owt-ucm method, with the notable advantage that we additionally produce a distribution over all possible tree-consistent segmentations of the image.