arxivst stuff from arxiv that you should probably bookmark

Object proposal generation applying the distance dependent Chinese restaurant process

Abstract · Apr 12, 2017 11:15 ·

superpixels term restaurant dependent likelihood object proposals robot proposal ddcrp cs-cv

Arxiv Abstract

  • Mikko Lauri
  • Simone Frintrop

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.

Read the paper (pdf) »