Abstract

The joint tasks of ob ject recognition and ob ject segmentation from a single image are complex in their requirement of not only correct classification, but also deciding exactly which pixels belong to the ob ject. Exploring all possible pixel subsets is prohibitively expensive, leading to recent approaches which use unsupervised image segmentation to re- duce the size of the configuration space. Image segmentation, however, is known to be unstable, strongly affected by small image perturbations, feature choices, or different segmentation algorithms. This instability has led to advocacy for using multiple segmentations of an image. In this pa- per, we explore the question of how to best integrate the information from multiple bottom-up segmentations of an image to improve ob ject recognition robustness. By integrating the image partition hypotheses in an intuitive combined top-down and bottom-up recognition approach, we improve ob ject and feature support. We further explore possible exten- sions of our method and whether they provide improved performance. Results are presented on the MSRC 21-class data set and the Pascal VOC2007 ob ject segmentation challenge.