# Object proposal generation applying the distance dependent Chinese restaurant process

## TL;DR

This paper introduces a non-parametric Bayesian method using the distance dependent Chinese restaurant process for object proposal generation, enabling uncertainty quantification and improved ranking of proposals in image segmentation tasks.

## Contribution

It presents a novel application of the distance dependent Chinese restaurant process for object proposals, incorporating likelihood estimation for better proposal ranking.

## Key findings

- Achieves state-of-the-art performance on indoor object discovery dataset.
- Provides a likelihood measure for each proposal to assess quality.
- Enables uncertainty quantification in object proposal generation.

## Abstract

In application domains such as robotics, it is useful to represent the uncertainty related to the robot's belief about the state of its environment. Algorithms that only yield a single "best guess" as a result are not sufficient. In this paper, we propose object proposal generation based on non-parametric Bayesian inference that allows quantification of the likelihood of the proposals. We apply Markov chain Monte Carlo to draw samples of image segmentations via the distance dependent Chinese restaurant process. Our method achieves state-of-the-art performance on an indoor object discovery data set, while additionally providing a likelihood term for each proposal. We show that the likelihood term can effectively be used to rank proposals according to their quality.